Triple
T4287199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hérault |
E97297
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Gard |
E89752
|
NE 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: Gard | Statement: [Hérault, borders, Gard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gard Context triple: [Hérault, borders, Gard]
-
A.
Gard
chosen
Gard is a department in southern France known for its Mediterranean landscapes, historic towns, and the famous Pont du Gard Roman aqueduct.
-
B.
Goytre
Goytre is a village and community located within the county borough of Neath Port Talbot in South Wales.
-
C.
Toft
Toft is a location that serves as one end of the Yell Sound ferry connection in the Shetland Islands, Scotland.
-
D.
Gudhjem
Gudhjem is a picturesque coastal village on the Danish island of Bornholm, known for its steep streets, red-roofed houses, and harbor overlooking the Baltic Sea.
-
E.
Plassans
Plassans is a fictional provincial town in southern France created by Émile Zola as a central setting in several of his Rougon-Macquart novels.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69b3454595848190a0e6bbb6a2bea040 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3505ef9fc81909c73e64bf77052ce |
completed | March 12, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5b7c8c1ac819086ded38c1abe9b63 |
completed | March 14, 2026, 7:32 p.m. |
Created at: March 12, 2026, 11:08 p.m.