Triple
T26698992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South China Sea maritime claims |
E673099
|
entity |
| Predicate | notableMapRepresentation |
P98670
|
FINISHED |
| Object | nine-dash line |
—
|
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: nine-dash line | Statement: [South China Sea maritime claims, notableMapRepresentation, nine-dash line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableMapRepresentation Context triple: [South China Sea maritime claims, notableMapRepresentation, nine-dash line]
-
A.
notableMap
chosen
Indicates that there is a map which is especially significant, well-known, or noteworthy in relation to the subject.
-
B.
geographicalRepresentation
Indicates that one entity serves as a geographic depiction, model, or mapping of another entity’s location, area, or spatial characteristics.
-
C.
mapsDepict
Indicates that maps visually represent or illustrate the geographic features, locations, or spatial relationships of something.
-
D.
mapsIn
Indicates that one entity is contained or represented within another entity as part of a mapping or map-like relationship.
-
E.
cartographicNotation
Indicates the specific symbols, labels, or graphical conventions used to represent geographic features or spatial information on a map.
- 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_69eecda2b49c8190a6c481cfc4c07954 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69ff0d80c0dc81909fbd12285c7a45c0 |
completed | May 9, 2026, 10:33 a.m. |
| PD | Predicate disambiguation | batch_69ff0cd03e78819094895058f925fbfa |
completed | May 9, 2026, 10:30 a.m. |
Created at: April 27, 2026, 3:30 a.m.