Triple

T14766085
Position Surface form Disambiguated ID Type / Status
Subject Glory Road E346999 entity
Predicate writer P1360 FINISHED
Object Bettina Gilois E581383 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: Bettina Gilois | Statement: [Glory Road, writer, Bettina Gilois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bettina Gilois
Context triple: [Glory Road, writer, Bettina Gilois]
  • A. Bettina Gilois chosen
    Bettina Gilois was a German-American screenwriter and author known for her work on inspirational, fact-based films such as "McFarland, USA" and "Glory Road."
  • B. Elisabeth Gortz
    Elisabeth Gortz was the wife of Danish-American social reformer and pioneering photojournalist Jacob Riis.
  • C. Johanna Loisinger
    Johanna Loisinger was an Austrian opera singer and actress best known as the morganatic wife of former Bulgarian ruler Alexander I.
  • D. Ruth Gikow
    Ruth Gikow was a Russian-born American painter and muralist known for her socially conscious, figurative depictions of urban life in mid-20th-century New York City.
  • E. Karin Brandauer
    Karin Brandauer was an Austrian film and theater director and screenwriter, known for her work in German-language cinema and her collaborations within the Central European arts scene.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7f576c881909da70627f5897c94 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7d279708190a54a56c0b80be10a completed May 9, 2026, 4:28 a.m.
Created at: April 10, 2026, 1:30 a.m.