Triple

T17693788
Position Surface form Disambiguated ID Type / Status
Subject Filip Wolski E441104 entity
Predicate coauthorWith P2389 FINISHED
Object Alec Radford E154209 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: Alec Radford | Statement: [Filip Wolski, coauthorWith, Alec Radford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alec Radford
Context triple: [Filip Wolski, coauthorWith, Alec Radford]
  • A. Alec Radford chosen
    Alec Radford is a machine learning researcher known for his influential work on generative models and large language models at OpenAI.
  • B. Alec Ramsey
    Alec Ramsey is the young boy protagonist of Walter Farley’s classic children’s novel series "The Black Stallion," known for his deep bond with a wild Arabian stallion.
  • C. Alec Mazo
    Alec Mazo is a professional ballroom dancer and choreographer best known for his appearances and championship win on the U.S. television show Dancing with the Stars.
  • D. Jeremy Ratchford
    Jeremy Ratchford is a Canadian actor best known for his role as Detective Nick Vera on the television crime drama "Cold Case."
  • E. Aidan Barclay
    Aidan Barclay is a British businessman and media executive, known for his role in managing the Barclay family’s business interests, including major publishing and retail assets.
  • 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_69d8b9e940b081908b862bb0e6e89b0d completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4715485d88190b9b6f347ff85d7c7 completed April 19, 2026, 6:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a02f82687b0819082ecb3cb9c883538 completed May 12, 2026, 9:51 a.m.
Created at: April 10, 2026, 10:04 a.m.