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.