Triple
T3329843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danube Delta |
E70006
|
entity |
| Predicate | coreDeltaArea |
P14400
|
FINISHED |
| Object | about 3,400 square kilometres |
—
|
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: about 3,400 square kilometres | Statement: [Danube Delta, coreDeltaArea, about 3,400 square kilometres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coreDeltaArea Context triple: [Danube Delta, coreDeltaArea, about 3,400 square kilometres]
-
A.
innerDeltaLocation
Indicates a spatial relationship where one location lies within the inner delta region of another geographic or hydrologic feature.
-
B.
areaCControl
Indicates that an entity exercises control or authority over a specific geographic area or region.
-
C.
formsDeltaAt
Indicates that one entity creates or gives rise to a change, difference, or deviation (a “delta”) in another entity at a specific point or context.
-
D.
hasDelta
Indicates that there is a change, difference, or deviation between two related states, values, or versions of something.
-
E.
hasCoreArea
chosen
Indicates that an entity possesses a primary or central area that is fundamental to its structure, function, or focus.
- 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_69ad85a24f208190bcf83131bfed3521 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb171ee0881908642504ab0ac8329 |
completed | March 8, 2026, 5:27 p.m. |
| PD | Predicate disambiguation | batch_69ada42a19348190a3862ce02451f4aa |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:12 p.m.