Triple

T3091127
Position Surface form Disambiguated ID Type / Status
Subject John Phillips E64483 entity
Predicate name P16 FINISHED
Object John Phillips unclear NED1 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: John Phillips | Statement: [John Phillips, name, John Phillips]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Phillips
Context triple: [John Phillips, name, John Phillips]
  • A. John Phillips
    John Phillips was a physician and medical leader best known as one of the founders of the Cleveland Clinic, a major academic medical center in the United States.
  • B. John Phillips
    John Phillips was an 18th-century American merchant and philanthropist best known for endowing and founding the prestigious Phillips Exeter Academy in New Hampshire.
  • C. David Chilton Phillips
    David Chilton Phillips was a British biophysicist and pioneering X-ray crystallographer known for his influential work on protein structure and leadership in structural biology.
  • D. Dennis Crosby
    Dennis Crosby was an American singer and actor best known as one of Bing Crosby’s sons who performed with his brothers as part of the Crosby family entertainment legacy.
  • E. Floyd Crosby
    Floyd Crosby was an Academy Award–winning American cinematographer known for his work on numerous classic films, including influential low-budget horror and science fiction movies.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69ad857c97d88190b26f9b1c90839c77 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada20eeee88190a5eecfce10e3848c completed March 8, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1f8a6fe2081909e2bf9ee5629f017 completed March 11, 2026, 11:20 p.m.
Created at: March 8, 2026, 3:03 p.m.