Triple

T20183389
Position Surface form Disambiguated ID Type / Status
Subject Some Kind of Wonderful E492789 entity
Predicate character P662 FINISHED
Object Watts 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: Watts | Statement: [Some Kind of Wonderful, character, Watts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Watts
Context triple: [Some Kind of Wonderful, character, Watts]
  • A. Watts
    Watts is a historic neighborhood in South Los Angeles known for its cultural significance, diverse community, and landmarks such as the Watts Towers.
  • B. Watts chosen
    Watts is a surname of English and Scottish origin, often associated with notable figures in science, arts, and public life.
  • C. Watts, Los Angeles
    Watts is a historically significant neighborhood in South Los Angeles known for its African American cultural heritage, the Watts Towers art landmark, and the 1965 Watts riots.
  • D. Compton
    Compton is a rural municipality in Quebec’s Estrie region, known for its agricultural landscape and proximity to the city of Sherbrooke.
  • E. Compton
    Compton is a common English surname borne by various notable individuals in science, politics, and the arts.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e668f068748190a0941e98ef5afd59 completed April 20, 2026, 5:57 p.m.
Created at: April 11, 2026, 11:36 p.m.