Triple

T4101144
Position Surface form Disambiguated ID Type / Status
Subject First Man E87942 entity
Predicate editor P1954 FINISHED
Object Tom Cross E221280 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: Tom Cross | Statement: [First Man, editor, Tom Cross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Cross
Context triple: [First Man, editor, Tom Cross]
  • A. Tom Cross chosen
    Tom Cross is an Academy Award–winning American film editor known for his work on acclaimed movies such as "Whiplash" and "La La Land."
  • B. Brian Rogers
    Brian Rogers is a film producer best known for his work on the 2014 reboot of the Godzilla franchise.
  • C. Mike Wheeler
    Mike Wheeler is a central character in the sci-fi horror series "Stranger Things," known as a loyal, determined member of the core friend group who helps confront supernatural threats in the town of Hawkins.
  • D. Ed Scott
    Ed Scott is a technology entrepreneur best known as a co-founder of BEA Systems, a major enterprise software company later acquired by Oracle.
  • E. Tom Ryan
    Tom Ryan is the central protagonist of the television series "The Unit," depicted as a highly skilled and seasoned leader of an elite U.S. Army special operations team.
  • 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_69aed94564cc8190a9c1457daedb6e7f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefd0ed168819093c83ba079d6725c completed March 9, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69b56b7833b081909bf5a87ee709b49f completed March 14, 2026, 2:06 p.m.
Created at: March 9, 2026, 3:40 p.m.