Triple
T13844729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valencia, Negros Oriental |
E332766
|
entity |
| Predicate | hasMountain |
P10602
|
FINISHED |
| Object | Mount Talinis |
E1072633
|
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: Mount Talinis | Statement: [Valencia, Negros Oriental, hasMountain, Mount Talinis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Talinis Context triple: [Valencia, Negros Oriental, hasMountain, Mount Talinis]
-
A.
Mount Talinis
chosen
Mount Talinis is a prominent volcanic mountain in Negros Oriental, Philippines, known for its challenging hiking trails, crater lakes, and rich biodiversity.
-
B.
Mount Butak
Mount Butak is a stratovolcano in East Java, Indonesia, known for its forested slopes and proximity to the Mount Kawi volcanic complex.
-
C.
Mount Wilis
Mount Wilis is a solitary, inactive stratovolcano in East Java, Indonesia, known for its forested slopes and surrounding rural highland communities.
-
D.
Mount Sinewit
Mount Sinewit is the highest mountain on the island of New Britain in Papua New Guinea.
-
E.
Mount Amba
Mount Amba is a hill in Kinshasa, Democratic Republic of the Congo, known primarily as the site of the University of Kinshasa.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02b1a25c8190a9f85ba43c421188 |
completed | April 14, 2026, 9:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbac802b7081909b36eebe85374594 |
completed | May 6, 2026, 9:02 p.m. |
Created at: April 9, 2026, 10:13 p.m.