Triple
T17240240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Monte Perdido Glacier |
E418472
|
entity |
| Predicate | nearestTown |
P350
|
FINISHED |
| Object | Torla-Ordesa |
E288725
|
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: Torla-Ordesa | Statement: [Monte Perdido Glacier, nearestTown, Torla-Ordesa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Torla-Ordesa Context triple: [Monte Perdido Glacier, nearestTown, Torla-Ordesa]
-
A.
Torla-Ordesa
chosen
Torla-Ordesa is a small mountain village in the Spanish Pyrenees that serves as the main gateway to the Ordesa y Monte Perdido National Park.
-
B.
Torelló
Torelló is a municipality in the comarca of Osona in Catalonia, Spain, known for its industrial heritage and scenic location in the Ter river valley.
-
C.
Sarralbe
Sarralbe is a small commune in northeastern France known for its location in the Moselle department near the German border.
-
D.
Tordera
Tordera is a municipality in the Maresme comarca of Catalonia, Spain, known for its rural landscapes and proximity to the Costa Brava.
-
E.
Adriasola
Adriasola is a Spanish-language surname, notably borne by Chilean lawyer and conservative political figure María Pía Adriasola.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e1f385c8190ae44e702923b6f66 |
completed | April 19, 2026, 1:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0170f1511c8190b70cb37e713a406a |
completed | May 11, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:39 a.m.