Triple

T16091602
Position Surface form Disambiguated ID Type / Status
Subject Corellia E390370 entity
Predicate homeworldOf P16439 FINISHED
Object Dengar E390497 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: Dengar | Statement: [Corellia, homeworldOf, Dengar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dengar
Context triple: [Corellia, homeworldOf, Dengar]
  • A. Dengar chosen
    Dengar is a Corellian bounty hunter in the Star Wars universe, known for working alongside other infamous hunters like Boba Fett during the search for the Millennium Falcon.
  • B. Dang
    Dang is a district in southwestern Nepal known for its fertile valleys, diverse ethnic communities, and role as a transport hub linking the Terai plains with the mid-hills.
  • C. Tengatangi
    Tengatangi is a small village settlement located on the island of Atiu in the Cook Islands.
  • D. Sekadau
    Sekadau is a town and regency capital in the Indonesian province of West Kalimantan on the island of Borneo.
  • E. Simak
    Simak is the surname of Clifford D. Simak, an American science fiction author renowned for his pastoral, humanistic storytelling.
  • 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1858d1264819099434d7201614d05 completed April 17, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb9550f0819092660f6c4b0d708e completed May 10, 2026, 2:21 a.m.
Created at: April 10, 2026, 4:59 a.m.