Triple
T30757468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haizhu Square |
E783127
|
entity |
| Predicate | hasNearbyRiverfront |
P186497
|
FINISHED |
| Object | Pearl River waterfront |
—
|
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: Pearl River waterfront | Statement: [Haizhu Square, hasNearbyRiverfront, Pearl River waterfront]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyRiverfront Context triple: [Haizhu Square, hasNearbyRiverfront, Pearl River waterfront]
-
A.
hasNearbyRiverStructure
Indicates that a river-related structure (such as a dam, bridge, or levee) is located close to the referenced entity.
-
B.
hasRiverfrontDistrict
Indicates that a place includes a designated district or area that directly borders and is oriented around a river.
-
C.
hasWaterfrontLocation
chosen
Indicates that an entity is situated directly adjacent to or along a body of water, such as a sea, lake, or river.
-
D.
hasWaterfrontPark
Indicates that a place or area includes or is associated with a park located directly along a body of water.
-
E.
locatedInRiverArea
Indicates that one entity is situated within the geographic area occupied by, adjacent to, or directly associated with a particular river.
- 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_69f224b047f48190b4f5efeb7ee97b37 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69feb8e856d48190aa34ad8ee8376e1c |
completed | May 9, 2026, 4:32 a.m. |
| PD | Predicate disambiguation | batch_69feb82a2b6c8190a473cc25976897be |
completed | May 9, 2026, 4:29 a.m. |
Created at: April 29, 2026, 8:39 p.m.