Triple
T23525482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antiguo |
E576419
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Mount Igeldo |
—
|
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: Mount Igeldo | Statement: [Antiguo, near, Mount Igeldo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Igeldo Context triple: [Antiguo, near, Mount Igeldo]
-
A.
Mount Igeldo
chosen
Mount Igeldo is a coastal hill and popular viewpoint overlooking the city and bay of San Sebastián in northern Spain.
-
B.
Mount Benacantil
Mount Benacantil is a prominent rocky hill in Alicante, Spain, best known for overlooking the city and hosting the historic Santa Bárbara Castle.
-
C.
Mount Isto
Mount Isto is a prominent peak in Alaska's remote Arctic region, notable for being the tallest mountain in the Brooks Range.
-
D.
Mount Fito
Mount Fito is the highest peak on the Samoan island of Upolu, known for its lush rainforest surroundings and central location within the island’s interior.
-
E.
Mount Falterona
Mount Falterona is a mountain in the Tuscan Apennines of Italy, known for its forested slopes and as the birthplace of the Arno River.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245f5a8848190a2ba42e271c6c31f |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1ac72bfb88190b7da3837e66e851c |
completed | April 29, 2026, 7 a.m. |
Created at: April 17, 2026, 6:09 p.m.