Triple

T23054414
Position Surface form Disambiguated ID Type / Status
Subject Nggela E574111 entity
Predicate neighboringLanguage P16383 FINISHED
Object Ghari E146328 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: Ghari | Statement: [Nggela, neighboringLanguage, Ghari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ghari
Context triple: [Nggela, neighboringLanguage, Ghari]
  • A. Ghari chosen
    Ghari is an Oceanic language spoken in the Solomon Islands, belonging to the Meso-Melanesian branch of the Austronesian language family.
  • B. Gharii
    Gharii is an alternative name for the entity known as Nggae, likely referring to the same person, place, or concept under a different designation.
  • C. Ghar
    Ghar is a 1978 Hindi drama film starring Rekha and Vinod Mehra, known for its sensitive portrayal of a married couple coping with trauma and its memorable R.D. Burman soundtrack.
  • D. Ghari Kapura
    Ghari Kapura is a town located in Pakistan’s Khyber Pakhtunkhwa province within the Mardan District.
  • E. Guzaarish
    Guzaarish is a 2010 Indian drama film directed by Sanjay Leela Bhansali that explores euthanasia through the story of a quadriplegic magician turned radio jockey.
  • 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_69e245ba7ae48190be606dbc54120e39 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1867eaed0819095c7da6b06101b12 completed April 29, 2026, 4:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c0ae217848190a2ecc1d008786a74 completed May 19, 2026, 7:01 a.m.
Created at: April 17, 2026, 3:54 p.m.