Triple

T14779832
Position Surface form Disambiguated ID Type / Status
Subject In Secret E347360 entity
Predicate stars P1956 FINISHED
Object Oscar Isaac E76856 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: Oscar Isaac | Statement: [In Secret, stars, Oscar Isaac]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oscar Isaac
Context triple: [In Secret, stars, Oscar Isaac]
  • A. Oscar Isaac chosen
    Oscar Isaac is a Guatemalan-American actor known for his versatile performances in films such as Inside Llewyn Davis, the Star Wars sequel trilogy, Ex Machina, and Dune.
  • B. Pablo Schreiber
    Pablo Schreiber is a Canadian-American actor known for his intense character roles in film and television, including standout performances in series like "Orange Is the New Black" and "American Gods."
  • C. Orson Cox
    Orson Cox is the son of Scottish actor and physicist-turned-science-communicator Brian Cox.
  • D. Andy García
    Andy García is a Cuban-American actor and director renowned for his roles in films such as "The Godfather Part III," "Ocean's Eleven," and "The Untouchables."
  • E. Adam P. Scott
    Adam P. Scott is a film editor known for his work on the science-fiction movie "City of Ember."
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deca9c7cac8190ba900df95e42e318 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0d00d46c8190b6289a9b8511a8fb completed May 8, 2026, 4:19 p.m.
Created at: April 10, 2026, 1:31 a.m.