Triple

T20863822
Position Surface form Disambiguated ID Type / Status
Subject Julian Mendelsohn E513693 entity
Predicate workedWith P398 FINISHED
Object Wang Chung 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: Wang Chung | Statement: [Julian Mendelsohn, workedWith, Wang Chung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wang Chung
Context triple: [Julian Mendelsohn, workedWith, Wang Chung]
  • A. Wang Chung chosen
    Wang Chung is a British new wave band best known for their 1980s hits and for composing the soundtrack to the film "To Live and Die in L.A."
  • B. Songhies
    Songhies is an alternate spelling of Songhees, a Coast Salish First Nation traditionally based around what is now Victoria on southern Vancouver Island in British Columbia, Canada.
  • C. Kohawks
    Kohawks is the athletic nickname and mascot for the sports teams representing Coe College in Cedar Rapids, Iowa.
  • D. Davichi
    Davichi is a South Korean female pop ballad duo known for their powerful vocals and numerous hit OST and chart-topping songs.
  • E. Nine Muses
    The Nine Muses are the goddesses of inspiration in Greek mythology, each presiding over a different art or science such as epic poetry, history, music, and dance.
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c45e51f08190ac1ff59280ad741b completed April 21, 2026, 12:27 a.m.
Created at: April 16, 2026, 12:44 p.m.