Triple

T10200619
Position Surface form Disambiguated ID Type / Status
Subject House of Isildur E238872 entity
Predicate hasMember P10 FINISHED
Object Arveleg I
Arveleg I was a King of Arthedain in J.R.R. Tolkien’s legendarium, a descendant of Isildur who ruled during the wars against Angmar.
 E847364 NE FINISHED

How this triple was built (4 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: Arveleg I | Statement: [House of Isildur, hasMember, Arveleg I]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Arveleg I
Context triple: [House of Isildur, hasMember, Arveleg I]
  • A. Arve
    The Arve is a river in southwestern Switzerland and southeastern France that flows through Geneva before joining the Rhône.
  • B. Hodal
    Hodal is a town in the Indian state of Haryana that forms part of the culturally significant Braj region associated with the legends of Lord Krishna.
  • C. Vallader
    Vallader is a major dialect of the Romansh language spoken primarily in Switzerland’s Lower Engadine region and used in local literature and education.
  • D. Herleve
    Herleve was the mother of William the Conqueror, traditionally described as a woman of modest Norman origins who became the mistress of Robert I, Duke of Normandy.
  • E. Espevær
    Espevær is a small island and fishing village in Vestland county, Norway, known for its traditional coastal culture and scenic maritime environment.
  • 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: Arveleg I
Triple: [House of Isildur, hasMember, Arveleg I]
Generated description
Arveleg I was a King of Arthedain in J.R.R. Tolkien’s legendarium, a descendant of Isildur who ruled during the wars against Angmar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Arveleg I
Target entity description: Arveleg I was a King of Arthedain in J.R.R. Tolkien’s legendarium, a descendant of Isildur who ruled during the wars against Angmar.
  • A. Arve
    The Arve is a river in southwestern Switzerland and southeastern France that flows through Geneva before joining the Rhône.
  • B. Hodal
    Hodal is a town in the Indian state of Haryana that forms part of the culturally significant Braj region associated with the legends of Lord Krishna.
  • C. Vallader
    Vallader is a major dialect of the Romansh language spoken primarily in Switzerland’s Lower Engadine region and used in local literature and education.
  • D. Herleve
    Herleve was the mother of William the Conqueror, traditionally described as a woman of modest Norman origins who became the mistress of Robert I, Duke of Normandy.
  • E. Espevær
    Espevær is a small island and fishing village in Vestland county, Norway, known for its traditional coastal culture and scenic maritime environment.
  • F. None of above. chosen

Provenance (5 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_69ca84e1ea088190b38162e43d4cfa8f completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdee3f3bac8190a63a81edffe7cda7 completed April 2, 2026, 4:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69d317f40f0c8190a3d966c934cc20f7 completed April 6, 2026, 2:18 a.m.
NEDg Description generation batch_69d3188886908190ba0a5539ce942980 completed April 6, 2026, 2:20 a.m.
NED2 Entity disambiguation (via description) batch_69d31c4fb8288190bbc6b3d4a79dafb1 completed April 6, 2026, 2:37 a.m.
Created at: March 30, 2026, 9:14 p.m.