Triple
T28869287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kobe Kosoku Line |
E729095
|
entity |
| Predicate | locatedUndergroundInSections |
P15152
|
FINISHED |
| Object | central Kobe |
—
|
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: central Kobe | Statement: [Kobe Kosoku Line, locatedUndergroundInSections, central Kobe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedUndergroundInSections Context triple: [Kobe Kosoku Line, locatedUndergroundInSections, central Kobe]
-
A.
undergroundZone
Indicates that something is located in, associated with, or occurring within an area beneath the ground surface.
-
B.
hasUndergroundSection
chosen
Indicates that an entity includes a portion or segment that is located below ground level.
-
C.
undergroundBranch
Indicates that one entity is a branch or extension of another that operates or exists in a hidden, secret, or non-public manner.
-
D.
hasUndergroundLevel
Indicates that one entity possesses or includes a level, floor, or section that is located below ground level.
-
E.
integratedIntoUnderground
Indicates that something has been incorporated or absorbed into an underground system, structure, or environment.
- 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_69f031a01cbc8190ba87270bb6fe4639 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69ffc7b4c7f88190b6357a44e7f0940f |
completed | May 9, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_69ffc755f09c8190995ca00d97336988 |
completed | May 9, 2026, 11:46 p.m. |
Created at: April 28, 2026, 6:49 a.m.