Triple
T35302178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Lokon and Mount Empung |
E1019533
|
entity |
| Predicate | sharesCraterComplex |
P113052
|
FINISHED |
| Object | Tompaluan crater |
—
|
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: Tompaluan crater | Statement: [Mount Lokon and Mount Empung, sharesCraterComplex, Tompaluan crater]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesCraterComplex Context triple: [Mount Lokon and Mount Empung, sharesCraterComplex, Tompaluan crater]
-
A.
partOfCraterSystem
chosen
Indicates that one crater is a component or subdivision of a larger, connected crater system.
-
B.
mainCrater
Indicates that one crater is the primary or most significant crater associated with another crater or crater-related feature.
-
C.
neighboringCrater
Indicates that one crater is located adjacent to or very close to another crater, such that they are considered neighbors on a surface.
-
D.
craterDescription
Indicates that a textual description is provided for a specific crater, detailing its characteristics or notable features.
-
E.
isSecondaryCraterOf
Indicates that one crater was formed by ejecta from the impact that created another, primary crater, rather than by a direct impact itself.
- F. None of above.
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_69f76de8b4c48190ae504b86185c474c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a005b2e0a9c819081c6f7ccbef49ff8 |
completed | May 10, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_6a005a8bcde88190ace2bc0215e26430 |
completed | May 10, 2026, 10:14 a.m. |
Created at: May 3, 2026, 4:03 p.m.