Triple

T22432454
Position Surface form Disambiguated ID Type / Status
Subject Gong E554530 entity
Predicate hasPart P35 FINISHED
Object Angel’s Egg E1536365 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’s Egg | Statement: [Gong, hasPart, Angel’s Egg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Angel’s Egg
Context triple: [Gong, hasPart, Angel’s Egg]
  • A. Angel’s Egg chosen
    Angel’s Egg is a 1985 avant-garde animated film directed by Mamoru Oshii, renowned for its minimal dialogue, surreal imagery, and philosophical, allegorical storytelling.
  • B. The Angel
    "The Angel" is a song by Bruce Springsteen from his debut album "Greetings from Asbury Park, N.J.," noted for its poetic lyrics and reflective, piano-driven style.
  • C. The Angel
    The Angel is an electronic music producer and DJ known for crafting atmospheric, dance-oriented tracks featured in underground club culture and film soundtracks.
  • D. The Angel
    The Angel is a film featuring British actor Adeel Akhtar in a prominent role.
  • E. The Angel
    The Angel is a historic British inn and public house, often noted for its traditional architecture and role as a local social and lodging landmark.
  • 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_69e11e5010e48190ae1e9c9db9697637 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15a3320448190ae3931062599116e completed April 29, 2026, 1:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b0c691e9881908734ed4f36baabba completed May 18, 2026, 12:56 p.m.
Created at: April 16, 2026, 8:47 p.m.