Triple

T36100494
Position Surface form Disambiguated ID Type / Status
Subject Bangkok Mass Transit System E1044191 entity
Predicate secondaryDepot P100462 FINISHED
Object Bang Wa Depot NE NERFINISHED

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: Bang Wa Depot | Statement: [Bangkok Mass Transit System, secondaryDepot, Bang Wa Depot]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: secondaryDepot
Context triple: [Bangkok Mass Transit System, secondaryDepot, Bang Wa Depot]
  • A. secondaryHub
    Indicates that an entity functions as a secondary or backup hub in relation to a primary hub within a network or system.
  • B. secondaryCargo
    Indicates that an entity serves as an additional or auxiliary cargo associated with a primary shipment or load.
  • C. secondarySite chosen
    Indicates that one entity serves as an additional or subordinate location associated with another primary site.
  • D. secondaryStorage
    Indicates that an entity serves as a secondary (non-primary) storage location or medium for another entity’s data or resources.
  • E. secondaryBranch
    Indicates that one entity functions as a secondary or subordinate branch in relation to another primary or main branch entity.
  • F. None of above.

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_69f76e338e2c8190b7f3bc68bec76349 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69ff5285ed74819097e6e2a9084a079a completed May 9, 2026, 3:28 p.m.
PD Predicate disambiguation batch_69ff51fbe28881908ac8417dff9db81a completed May 9, 2026, 3:25 p.m.
Created at: May 3, 2026, 4:08 p.m.