Triple

T1787637
Position Surface form Disambiguated ID Type / Status
Subject Titanic E39425 entity
Predicate editedBy P1954 FINISHED
Object Conrad Buff E116007 NE FINISHED

How this triple was built (2 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: Conrad Buff | Statement: [Titanic, editedBy, Conrad Buff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Conrad Buff
Context triple: [Titanic, editedBy, Conrad Buff]
  • A. Conrad Buff IV chosen
    Conrad Buff IV is an American film editor known for his work on major Hollywood productions, including blockbusters like "Terminator Salvation."
  • B. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • C. Henry Gordon Bennett
    Henry Gordon Bennett was an Australian Army lieutenant general best known for his controversial leadership during World War II, particularly in the Malayan campaign and the fall of Singapore.
  • D. Clay Benchley
    Clay Benchley is one of the children of Peter Benchley, the American author best known for writing the novel "Jaws."
  • E. Douglas Clifton Brown
    Douglas Clifton Brown was a British Conservative politician who served as Speaker of the House of Commons during the Second World War and the early postwar period.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa650fd3448190a6a2c979db982cae completed March 6, 2026, 5:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69adb5ce137481909fde04dfa2d6a45a completed March 8, 2026, 5:45 p.m.
Created at: March 4, 2026, 7:32 p.m.