Triple
T8525330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orb River |
E201799
|
entity |
| Predicate | notableStructureOn |
P61000
|
FINISHED |
| Object | Canal du Midi aqueduct over the Orb at Béziers |
—
|
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: Canal du Midi aqueduct over the Orb at Béziers | Statement: [Orb River, notableStructureOn, Canal du Midi aqueduct over the Orb at Béziers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableStructureOn Context triple: [Orb River, notableStructureOn, Canal du Midi aqueduct over the Orb at Béziers]
-
A.
notablePlace
Indicates that a place is especially significant, famous, or noteworthy in relation to the subject.
-
B.
notableLocationFeature
Indicates that a location is characterized or distinguished by a particular notable physical or contextual feature.
-
C.
notableLocation
Indicates that a location is especially significant, prominent, or noteworthy in relation to the subject.
-
D.
notableBuildingAssociated
Indicates a relationship where a notable or significant building is associated with, connected to, or relevant to a given entity.
-
E.
notableFeatureOn
chosen
Indicates that one entity is a prominent or distinguishing feature located on or part of another entity.
- 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_69ca83228b24819085d22e7dc99f5d94 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe644c4648190a14dcaeaa90d72c7 |
completed | March 31, 2026, 3:20 p.m. |
| PD | Predicate disambiguation | batch_69cbd10f64b4819080859057c19e58f0 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:16 p.m.