Triple
T33704805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caohe Street Bridge |
E863556
|
entity |
| Predicate | isInWaterTown |
P135498
|
FINISHED |
| Object | Zhujiajiao ancient town |
—
|
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: Zhujiajiao ancient town | Statement: [Caohe Street Bridge, isInWaterTown, Zhujiajiao ancient town]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInWaterTown Context triple: [Caohe Street Bridge, isInWaterTown, Zhujiajiao ancient town]
-
A.
hasWaterTown
Indicates that one place is a town characterized by or associated with water in relation to another entity.
-
B.
locatedInWaterfrontTown
chosen
Indicates that the subject is situated within a town that is directly adjacent to or closely associated with a body of water, such as a sea, lake, or river.
-
C.
hasNearbyWater
Indicates that one entity is located close to a body of water associated with or relevant to another entity.
-
D.
isWaterfrontSettlement
Indicates that a settlement is located directly adjacent to a body of water, such as a sea, lake, or river.
-
E.
isInCountryWater
Indicates that one entity (typically a body of water or water area) is located within or belongs to the territorial waters of a specified country.
- 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_69f3498844608190bb8f9b14908d2510 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fab37f808190b82fe40f3cbe1e9b |
completed | May 3, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:43 a.m.