Triple

T14489368
Position Surface form Disambiguated ID Type / Status
Subject Lorde E359322 entity
Predicate notableWork P4 FINISHED
Object Green Light E988165 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: Green Light | Statement: [Lorde, notableWork, Green Light]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Green Light
Context triple: [Lorde, notableWork, Green Light]
  • A. Green Light
    "Green Light" is an upbeat, dance-pop and R&B single by John Legend featuring André 3000, known for its energetic tempo and departure from Legend’s usual soulful ballad style.
  • B. Green Light
    "Green Light" is an upbeat R&B-pop song by Beyoncé, known for its brassy production, assertive lyrics, and energetic vocal performance.
  • C. Green Light
    "Green Light" is a 1935 American drama film, adapted from Lloyd C. Douglas's novel, for which Samson Raphaelson wrote the screenplay.
  • D. Green Light
    "Green Light" is a 1982 blues-rock album by American singer-songwriter and guitarist Bonnie Raitt, showcasing her blend of rock, blues, and roots influences.
  • E. Greenlight chosen
    "Greenlight" is a song by the New Zealand singer-songwriter Lorde from her 2017 album "Melodrama."
  • 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_69d8279740308190af9df93a3af8592e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de930bd1d48190abd6c47da0a3ebc8 completed April 14, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d90f86081908b25f3eb90042c73 completed May 8, 2026, 4:58 a.m.
Created at: April 10, 2026, 1:20 a.m.