Triple

T147321
Position Surface form Disambiguated ID Type / Status
Subject Old High German E3358 entity
Predicate notableText P7250 FINISHED
Object Hildebrandslied
Hildebrandslied is an early medieval Old High German heroic poem that recounts a tragic duel between a father and son and is one of the oldest surviving works in the German language.
E17592 NE FINISHED

How this triple was built (5 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Hildebrandslied | Statement: [Old High German, notableText, Hildebrandslied]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hildebrandslied
Context triple: [Old High German, notableText, Hildebrandslied]
  • A. Norse sagas
    Norse sagas are medieval Icelandic prose narratives that recount the legendary heroes, gods, and historical events of the Norse and wider Scandinavian world.
  • B. Sir Gawain and the Green Knight
    Sir Gawain and the Green Knight is a late 14th-century Middle English chivalric romance poem that tells the story of King Arthur’s knight Sir Gawain and his beheading game encounter with the mysterious Green Knight.
  • C. Heer
    The Heer was the land-based component of Nazi Germany’s armed forces, serving as its primary army during World War II.
  • D. Chant de guerre pour l’Armée du Rhin
    Chant de guerre pour l’Armée du Rhin is the original revolutionary war song composed in 1792 by Claude Joseph Rouget de Lisle that later became known as “La Marseillaise,” the French national anthem.
  • E. Vikingskipet
    Vikingskipet is an indoor speed skating arena in Hamar, Norway, renowned for hosting major international competitions including events at the 1994 Winter Olympics.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hildebrandslied
Triple: [Old High German, notableText, Hildebrandslied]
Generated description
Hildebrandslied is an early medieval Old High German heroic poem that recounts a tragic duel between a father and son and is one of the oldest surviving works in the German language.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hildebrandslied
Target entity description: Hildebrandslied is an early medieval Old High German heroic poem that recounts a tragic duel between a father and son and is one of the oldest surviving works in the German language.
  • A. Norse sagas
    Norse sagas are medieval Icelandic prose narratives that recount the legendary heroes, gods, and historical events of the Norse and wider Scandinavian world.
  • B. Sir Gawain and the Green Knight
    Sir Gawain and the Green Knight is a late 14th-century Middle English chivalric romance poem that tells the story of King Arthur’s knight Sir Gawain and his beheading game encounter with the mysterious Green Knight.
  • C. Heer
    The Heer was the land-based component of Nazi Germany’s armed forces, serving as its primary army during World War II.
  • D. Chant de guerre pour l’Armée du Rhin
    Chant de guerre pour l’Armée du Rhin is the original revolutionary war song composed in 1792 by Claude Joseph Rouget de Lisle that later became known as “La Marseillaise,” the French national anthem.
  • E. Vikingskipet
    Vikingskipet is an indoor speed skating arena in Hamar, Norway, renowned for hosting major international competitions including events at the 1994 Winter Olympics.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: notableText
Context triple: [Old High German, notableText, Hildebrandslied]
  • A. notableFor
    Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
  • B. notablePrimary
    Indicates that one entity is the main or most prominent example, instance, or representative of another entity.
  • C. notableSingle
    Indicates that the subject is particularly recognized or distinguished for one specific, individual instance (such as a single work, event, or achievement).
  • D. notableEditor
    Indicates that an entity has served as a significant or distinguished editor of another entity, such as a publication or work.
  • E. notableStandard
    Indicates that one entity is a widely recognized or influential standard that the other entity is associated with or exemplifies.
  • F. None of above. chosen

Provenance (7 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a252868de4819080e21c9938bfe8b6 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a258808ff08190a06b6206f635612b completed Feb. 28, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2c27754a881908ef5a96e05e515e3 completed Feb. 28, 2026, 10:24 a.m.
NEDg Description generation batch_69a2c37177348190857d52872e6ab393 completed Feb. 28, 2026, 10:29 a.m.
NED2 Entity disambiguation (via description) batch_69a2c3c512f08190bb87f874524b1616 completed Feb. 28, 2026, 10:30 a.m.
PD Predicate disambiguation batch_69a256580c2c8190beecca60ca8595f3 completed Feb. 28, 2026, 2:43 a.m.
PDg Predicate description generation batch_69a2587e598c81909e1082b813971f48 completed Feb. 28, 2026, 2:52 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.