Triple

T14501956
Position Surface form Disambiguated ID Type / Status
Subject Janis Winehouse E340163 entity
Predicate givenName P17 FINISHED
Object Janis E358888 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: Janis | Statement: [Janis Winehouse, givenName, Janis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janis
Context triple: [Janis Winehouse, givenName, Janis]
  • A. Janis chosen
    Janis is a given name, often used as a variant of Janice, that can be masculine or feminine depending on cultural context.
  • B. Janis Ian
    Janis Ian is a sharp-witted, artsy outsider and key protagonist in the teen comedy film "Mean Girls," known for orchestrating a plan to take down the school's popular clique.
  • C. Janis Ian
    Janis Ian is an American singer-songwriter best known for her introspective folk and pop songs, including the Grammy-winning hit "At Seventeen."
  • D. Emily Ruth May
    Emily Ruth May is a daughter of Queen guitarist and astrophysicist Brian May.
  • E. Joni
    Joni is a thoughtful, college-bound teenage daughter in the film "The Kids Are All Right," whose curiosity about her sperm-donor father helps drive the story’s family drama.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de94e0f9048190a2d266cfa4f9dfb6 completed April 14, 2026, 7:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d9b6f7481908b7eb76226a93545 completed May 8, 2026, 4:59 a.m.
Created at: April 10, 2026, 1:21 a.m.