Triple

T18754264
Position Surface form Disambiguated ID Type / Status
Subject Kaohsiung 17LIVE Steelers E458606 entity
Predicate hasSponsor P35686 FINISHED
Object 17LIVE 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: 17LIVE | Statement: [Kaohsiung 17LIVE Steelers, hasSponsor, 17LIVE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 17LIVE
Context triple: [Kaohsiung 17LIVE Steelers, hasSponsor, 17LIVE]
  • A. 17LIVE chosen
    17LIVE is a live-streaming platform and entertainment company known for interactive video content and real-time creator–audience engagement.
  • B. 1LIVE
    1LIVE is a popular German public radio station aimed primarily at young listeners, known for contemporary music, entertainment, and youth-oriented programming.
  • C. V LIVE
    V LIVE is a South Korean live video streaming service, especially popular for K-pop idols and celebrities to broadcast and interact with fans in real time.
  • D. Free Live!
    Free Live! is a live album by the English rock band Free, capturing their energetic early-1970s performances.
  • E. Channel Live
    Channel Live is a 1990s American hip hop duo best known for their politically charged, KRS-One-affiliated single “Mad Izm.”
  • 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e579ef4ee48190a9892ac9787ffe37 completed April 20, 2026, 12:57 a.m.
Created at: April 10, 2026, 11:51 a.m.