Triple

T8425164
Position Surface form Disambiguated ID Type / Status
Subject Sting International E198964 entity
Predicate coWrote P7732 FINISHED
Object “Angel” E733216 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: “Angel” | Statement: [Sting International, coWrote, “Angel”]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: “Angel”
Context triple: [Sting International, coWrote, “Angel”]
  • A. “Angel” chosen
    "Angel" is a popular reggae fusion song by Shaggy featuring Rayvon, known for its smooth melody and romantic lyrics.
  • B. "The Angel Child"
    "The Angel Child" is a short story by Stephen Crane, included in his Whilomville Stories collection, depicting small-town American life through the experiences of a precocious child.
  • C. Love Angel
    Love Angel is a song written by acclaimed R&B songwriter Johntá Austin.
  • D. No Angel
    No Angel is a comic book series written by Eric Palicki that blends supernatural horror with family drama and religious themes.
  • E. Voice of an Angel
    Voice of an Angel is the debut classical crossover album by Welsh soprano Charlotte Church, released when she was a young teenager and noted for showcasing her remarkable vocal talent.
  • 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_69ca8312d63c8190bf133b676b44a385 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cb85a2871081908a4093838fc93b5a completed March 31, 2026, 8:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce1d502c448190aabc957786bde79f completed April 2, 2026, 7:40 a.m.
Created at: March 30, 2026, 6:07 p.m.