Triple

T1725796
Position Surface form Disambiguated ID Type / Status
Subject Ors Communal Cemetery E37492 entity
Predicate locatedIn P40 FINISHED
Object Ors
Ors is a small commune in northern France, known for its World War I history and military cemetery.
 E194825 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: Ors | Statement: [Ors Communal Cemetery, locatedIn, Ors]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ors
Context triple: [Ors Communal Cemetery, locatedIn, Ors]
  • A. Ourthe
    The Ourthe is a scenic river in southeastern Belgium that flows through the Ardennes region, known for its winding valleys, outdoor recreation, and picturesque towns.
  • B. Orb
    The Orb is a river in southern France that flows through the Occitanie region before emptying into the Mediterranean Sea.
  • C. ORC
    ORC (Optimized Row Columnar) is a highly efficient, columnar storage file format commonly used in big data systems to enable fast analytics and compression.
  • D. Orr
    Orr is a surname of Scottish origin most famously associated with legendary Canadian ice hockey defenseman Bobby Orr.
  • E. Orit
    Orit is the traditional biblical canon of Ethiopian Jews, encompassing their sacred scriptures and guiding religious teachings.
  • 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: Ors
Triple: [Ors Communal Cemetery, locatedIn, Ors]
Generated description
Ors is a small commune in northern France, known for its World War I history and military cemetery.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ors
Target entity description: Ors is a small commune in northern France, known for its World War I history and military cemetery.
  • A. Ourthe
    The Ourthe is a scenic river in southeastern Belgium that flows through the Ardennes region, known for its winding valleys, outdoor recreation, and picturesque towns.
  • B. Orb
    The Orb is a river in southern France that flows through the Occitanie region before emptying into the Mediterranean Sea.
  • C. ORC
    ORC (Optimized Row Columnar) is a highly efficient, columnar storage file format commonly used in big data systems to enable fast analytics and compression.
  • D. Orr
    Orr is a surname of Scottish origin most famously associated with legendary Canadian ice hockey defenseman Bobby Orr.
  • E. Orit
    Orit is the traditional biblical canon of Ethiopian Jews, encompassing their sacred scriptures and guiding religious teachings.
  • 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_69a8861acab88190bb43cde203429399 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa635cad5481908e6c04a230d3b0bb completed March 6, 2026, 5:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8af329a481908cbd3cf351fabfd5 completed March 8, 2026, 2:42 p.m.
NEDg Description generation batch_69ad957ce41881909f1e214ebf4b08a4 completed March 8, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_69ad97b479bc81908b5f75b5df41f577 completed March 8, 2026, 3:37 p.m.
Created at: March 4, 2026, 7:30 p.m.