Triple
T10616386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pinghu City |
E276130
|
entity |
| Predicate | across |
P94992
|
FINISHED |
| Object | Hangzhou Bay from Shanghai |
—
|
LITERAL 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: Hangzhou Bay from Shanghai | Statement: [Pinghu City, across, Hangzhou Bay from Shanghai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: across Context triple: [Pinghu City, across, Hangzhou Bay from Shanghai]
-
A.
crossingOf
Indicates that one entity serves as the intersection or crossing point of two or more linear features, such as roads, paths, or tracks.
-
B.
crossedBy
Indicates that one entity (typically a path, line, or boundary) is intersected or traversed by another entity.
-
C.
runsAcross
Indicates that one entity moves quickly on foot from one side of another entity, area, or boundary to the opposite side, traversing it in a roughly straight path.
-
D.
usedAcross
Indicates that something is utilized or applied in multiple different contexts, locations, or domains.
-
E.
crossCut
Indicates that one entity intersects or passes through another, typically cutting across it from one side to the other.
- F. None of above. chosen
Provenance (4 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_69d6aaf948d88190806cc3a8c47a3fb2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d6df6d76dc8190bd8d481fed3225d9 |
completed | April 8, 2026, 11:06 p.m. |
| PD | Predicate disambiguation | batch_69d6dd7a223c8190854409d76368f3e8 |
completed | April 8, 2026, 10:58 p.m. |
| PDg | Predicate description generation | batch_69d6df463ea8819091d6683e476b4f21 |
completed | April 8, 2026, 11:05 p.m. |
Created at: April 8, 2026, 7:33 p.m.