Triple

T22683462
Position Surface form Disambiguated ID Type / Status
Subject Jean Brooks E560844 entity
Predicate name P16 FINISHED
Object Jean Brooks NE NERFINISHED

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: Jean Brooks | Statement: [Jean Brooks, name, Jean Brooks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean Brooks
Context triple: [Jean Brooks, name, Jean Brooks]
  • A. Jean Brooks chosen
    Jean Brooks was an American film actress of the 1930s and 1940s, best known for her roles in horror and mystery films produced by RKO Pictures.
  • B. Nat Borchers
    Nat Borchers is a retired American soccer defender best known for his long, stalwart career in Major League Soccer and his key role in helping Real Salt Lake win the 2009 MLS Cup.
  • C. Brooks Hatlen
    Brooks Hatlen is an elderly prison librarian in "The Shawshank Redemption" whose tragic struggle to adapt to life outside prison highlights the film’s themes of institutionalization and hopelessness.
  • D. Delle Bolton
    Delle Bolton is an American actress best known for her role as the Native American woman Swan in the 1972 Western film "Jeremiah Johnson."
  • E. Shepard Brooks
    Shepard Brooks was a prominent 19th-century Chicago real estate developer and businessman known for commissioning landmark commercial buildings such as the Rookery Building.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1786204d88190a837a5f04e16e94c completed April 29, 2026, 3:17 a.m.
Created at: April 17, 2026, 3:12 p.m.