Triple
T2583028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spratly Islands |
E57135
|
entity |
| Predicate | hasNumberOfFeatures |
P7181
|
FINISHED |
| Object | more than 100 maritime features |
—
|
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: more than 100 maritime features | Statement: [Spratly Islands, hasNumberOfFeatures, more than 100 maritime features]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNumberOfFeatures Context triple: [Spratly Islands, hasNumberOfFeatures, more than 100 maritime features]
-
A.
isFeatureLength
Indicates that something (typically a film or video) has a duration long enough to be considered a full-length, standard feature.
-
B.
hasNumberOfPoints
chosen
Indicates that an entity is associated with a specific count of points it possesses or comprises.
-
C.
hasDistinctFeature
Indicates that an entity possesses a specific characteristic or attribute that differentiates it from others.
-
D.
hasFeatureID
Indicates that an entity is associated with a specific feature identified by a unique ID.
-
E.
hasFeature
Indicates that an entity possesses, exhibits, or includes a particular characteristic, attribute, or component.
- 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_69ab4a4dca6481908c301f8e317396e7 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd3c9d0548190b29743ac1d7837ff |
completed | March 7, 2026, 7:29 a.m. |
| PD | Predicate disambiguation | batch_69abd0cfeae08190aed03866ba071c5c |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:49 p.m.