Triple

T4356057
Position Surface form Disambiguated ID Type / Status
Subject Die Hard E98150 entity
Predicate screenwriter P2831 FINISHED
Object Steven E. de Souza E345336 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: Steven E. de Souza | Statement: [Die Hard, screenwriter, Steven E. de Souza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steven E. de Souza
Context triple: [Die Hard, screenwriter, Steven E. de Souza]
  • A. Steven E. de Souza chosen
    Steven E. de Souza is an American screenwriter and producer best known for writing blockbuster action films such as "Die Hard" and "48 Hrs."
  • B. Michael T. Williamson
    Michael T. Williamson is an American actor best known for his role as Benjamin Buford "Bubba" Blue in the film Forrest Gump.
  • C. Stephen M. Kellen
    Stephen M. Kellen was a prominent financier and philanthropist known for his leadership at Arnhold and S. Bleichroeder and his significant support of cultural and educational institutions.
  • D. David Scearce
    David Scearce is a Canadian screenwriter best known for adapting Christopher Isherwood’s novel into the acclaimed film "A Single Man."
  • E. Michael T. Sauer
    Michael T. Sauer was an American judge best known for presiding over high-profile criminal cases in Los Angeles County.
  • 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_69b3454965f881908c41190bb22f0e4b completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b351c5773481908446d84897e7a533 completed March 12, 2026, 11:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5e501671c8190bf8a9998f46a9f3b completed March 14, 2026, 10:45 p.m.
Created at: March 12, 2026, 11:16 p.m.