Triple

T12901503
Position Surface form Disambiguated ID Type / Status
Subject Neelix E308621 entity
Predicate romanticPartner P9994 FINISHED
Object Kes E308622 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: Kes | Statement: [Neelix, romanticPartner, Kes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kes
Context triple: [Neelix, romanticPartner, Kes]
  • A. Kes
    Kes is a 1969 British drama film directed by Ken Loach, widely acclaimed for its realistic portrayal of a working-class boy in Northern England who finds solace in training a kestrel.
  • B. Kes chosen
    Kes is an Ocampa crew member on Star Trek: Voyager, known for her short lifespan, strong empathic and telepathic abilities, and close relationships with Neelix and the Doctor.
  • C. Kees
    Kees is the familiar nickname of Kees van Dongen, a prominent Dutch-French Fauvist painter known for his vibrant colors and expressive portraits.
  • D. Ke
    Ke is the given name of Ke Huy Quan, the Vietnamese-American actor and former child star known for roles in films like "Indiana Jones and the Temple of Doom," "The Goonies," and "Everything Everywhere All at Once."
  • E. Kais
    Kais is the given name of Kais Saied, the Tunisian politician and president known for his anti-corruption stance and consolidation of executive power.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97180ee708190b60a3e58c42f764f completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a56189b081909ed838addcb6d265 completed May 3, 2026, 1:31 a.m.
Created at: April 9, 2026, 5:40 p.m.