Triple
T24672147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arize River |
E610869
|
entity |
| Predicate | hasNotableSiteOnBanks |
P8340
|
FINISHED |
| Object | Grotte du Mas-d’Azil |
—
|
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: Grotte du Mas-d’Azil | Statement: [Arize River, hasNotableSiteOnBanks, Grotte du Mas-d’Azil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableSiteOnBanks Context triple: [Arize River, hasNotableSiteOnBanks, Grotte du Mas-d’Azil]
-
A.
hasLandmarkOnBank
chosen
Indicates that a landmark is located on the bank (shore or edge) of a geographic feature such as a river, lake, or canal.
-
B.
hasBankOn
Indicates that one entity is located on or alongside the bank (edge) of another entity, typically a river, lake, or similar body.
-
C.
hasCityOnBank
Indicates that a city is located on the bank of a particular river or body of water.
-
D.
hasDistrictOnBanks
Indicates that a district is located along or adjacent to the banks of a river or similar water body.
-
E.
hasBank
Indicates that one entity possesses, is associated with, or is served by a particular bank (such as a financial institution or river bank).
- 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_69e2c4d505cc8190981881df06c0bf52 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f47b865df48190bf4b6d3e9f9305e6 |
completed | May 1, 2026, 10:08 a.m. |
| PD | Predicate disambiguation | batch_69f4682c8a3c8190adbfaac99474eaaf |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 18, 2026, 2:47 a.m.