Triple

T830975
Position Surface form Disambiguated ID Type / Status
Subject Audie Murphy E17964 entity
Predicate givenName P17 FINISHED
Object Audie
Audie is a given name most famously associated with Audie Murphy, one of the most decorated American combat soldiers of World War II and later a Hollywood actor.
 E108549 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: Audie | Statement: [Audie Murphy, givenName, Audie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Audie
Context triple: [Audie Murphy, givenName, Audie]
  • A. Leslie
    Leslie is the given name of Leslie R. Groves Jr., the U.S. Army Corps of Engineers officer who directed the Manhattan Project during World War II.
  • B. Leslie
    Leslie is a Toronto subway station on Line 4 Sheppard in the city's transit system.
  • C. Leslie
    Leslie is a small town in Fife, Scotland, situated near Glenrothes and known historically for its textile and papermaking industries.
  • D. Nance
    Nance is the middle name of John Nance Garner, the 32nd vice president of the United States under Franklin D. Roosevelt.
  • E. Lloyd
    Lloyd is the middle name of William Lloyd Garrison, the prominent 19th-century American abolitionist and social reformer.
  • 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: Audie
Triple: [Audie Murphy, givenName, Audie]
Generated description
Audie is a given name most famously associated with Audie Murphy, one of the most decorated American combat soldiers of World War II and later a Hollywood actor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Audie
Target entity description: Audie is a given name most famously associated with Audie Murphy, one of the most decorated American combat soldiers of World War II and later a Hollywood actor.
  • A. Leslie
    Leslie is the given name of Leslie R. Groves Jr., the U.S. Army Corps of Engineers officer who directed the Manhattan Project during World War II.
  • B. Leslie
    Leslie is a Toronto subway station on Line 4 Sheppard in the city's transit system.
  • C. Leslie
    Leslie is a small town in Fife, Scotland, situated near Glenrothes and known historically for its textile and papermaking industries.
  • D. Nance
    Nance is the middle name of John Nance Garner, the 32nd vice president of the United States under Franklin D. Roosevelt.
  • E. Lloyd
    Lloyd is the middle name of William Lloyd Garrison, the prominent 19th-century American abolitionist and social reformer.
  • 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_69a4937c9c188190aaa216f6b466f452 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4abb4be948190ae757df85bdc40e4 completed March 1, 2026, 9:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7cf51a5608190a739b16078f4dfb0 completed March 4, 2026, 6:21 a.m.
NEDg Description generation batch_69a7d04b92188190bf04dddab69c6e6e completed March 4, 2026, 6:25 a.m.
NED2 Entity disambiguation (via description) batch_69a7d11309bc8190a2f02e9b2e0ec531 completed March 4, 2026, 6:28 a.m.
Created at: March 1, 2026, 7:38 p.m.