Triple

T5055295
Position Surface form Disambiguated ID Type / Status
Subject Ursula Andress E113885 entity
Predicate workedWith P398 FINISHED
Object Harry Hamlin E295346 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: Harry Hamlin | Statement: [Ursula Andress, workedWith, Harry Hamlin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Hamlin
Context triple: [Ursula Andress, workedWith, Harry Hamlin]
  • A. Harry Hamlin chosen
    Harry Hamlin is an American actor best known for his roles in the film "Clash of the Titans" and the television series "L.A. Law."
  • B. Hamlin
    Hamlin is a surname most notably associated with Hannibal Hamlin, who served as vice president of the United States under Abraham Lincoln during the Civil War.
  • C. Howard Koh
    Howard Koh is an American physician and public health leader who served as the U.S. Assistant Secretary for Health and is known for his work in cancer prevention, health disparities, and tobacco control.
  • D. David Barron
    David Barron is a British film producer best known for his extensive work on the Harry Potter film series.
  • E. John Curtis Estes
    John Curtis Estes is the birth name of John Holmes, a notorious American adult film actor who became one of the most famous pornographic performers of the 1970s and 1980s.
  • 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_69bd443aa1f88190abb992d138f2cf42 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd744ccb888190a8a0ddd7c4d62f35 completed March 20, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb0fd25c081909ddf2d8eb77f33e7 completed March 21, 2026, 2:53 p.m.
Created at: March 20, 2026, 1:38 p.m.