Triple
T37547184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 中沙群岛 |
E933494
|
entity |
| Predicate | 所属更大地理单元 |
P176599
|
FINISHED |
| Object | 中国南海诸岛 |
—
|
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: 中国南海诸岛 | Statement: [中沙群岛, 所属更大地理单元, 中国南海诸岛]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所属更大地理单元 Context triple: [中沙群岛, 所属更大地理单元, 中国南海诸岛]
-
A.
hasEvenHigherGeographicUnit
chosen
Indicates that one geographic unit is directly contained within or subordinate to another geographic unit at a higher hierarchical level.
-
B.
isPoliticalGeographicUnit
Indicates that an entity functions as a defined geographic area used for political or administrative purposes, such as governance, representation, or jurisdiction.
-
C.
regionCorrespondsRoughlyTo
Indicates that one region approximately matches or aligns with another in location, extent, or boundaries, but not with precise or exact correspondence.
-
D.
geographicDivision
Indicates that one place is an administrative or territorial subdivision of another place.
-
E.
geologicUnitOf
Indicates that one entity is a geologic unit to which the other entity belongs or with which it is associated.
- 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_69f76eca55bc8190acf25741793d5dac |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.