Triple
T13560042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Col du Pourtalet |
E323881
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Laruns |
E303993
|
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: Laruns | Statement: [Col du Pourtalet, nearbySettlement, Laruns]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laruns Context triple: [Col du Pourtalet, nearbySettlement, Laruns]
-
A.
Laruns
chosen
Laruns is a commune in southwestern France nestled in the Pyrenees, known as a gateway to the Ossau Valley and nearby mountain passes and spa towns.
-
B.
Ornsay
Ornsay is a small Scottish island located off the coast of the Isle of Skye, known for its scenic lighthouse and views over the Sound of Sleat.
-
C.
Ulsta
Ulsta is a small settlement on the island of Yell in Shetland, Scotland, known primarily for its ferry terminal linking Yell to the Shetland mainland.
-
D.
Harestua
Harestua is a village in Viken county, Norway, known for its residential community and proximity to the Harestua Solar Observatory.
-
E.
Tyvholm
Tyvholm is one of the small Danish islands that form part of the Hirsholmene archipelago in the Kattegat.
- 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaff5219081909cf60423e79d278f |
completed | April 12, 2026, 2:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f75dab4974819097880ad4d50f1b34 |
completed | May 3, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:47 p.m.