Triple
T15197956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Finkol |
E363186
|
entity |
| Predicate | hasRunoffTo |
P100480
|
FINISHED |
| Object | streams on Kosrae |
—
|
LITERAL 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: streams on Kosrae | Statement: [Mount Finkol, hasRunoffTo, streams on Kosrae]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRunoffTo Context triple: [Mount Finkol, hasRunoffTo, streams on Kosrae]
-
A.
hasRunoffDirection
chosen
Indicates the direction in which runoff (such as water or other liquid) flows or is directed from a given source or surface.
-
B.
hasRunoffAreas
Indicates that an entity includes or is equipped with designated runoff areas for managing excess water or liquid flow.
-
C.
mainPresidentialRunoffCandidates
Indicates that the related entities are the primary candidates participating in a presidential election runoff.
-
D.
runoffElectionDay
Indicates the day on which a runoff election is held to determine a winner when no candidate achieved the required threshold in a prior election.
-
E.
hasOfficeContested
Indicates that an individual has been a candidate for a particular public office in an election.
- 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e006b476208190a5119710c518bb1f |
completed | April 15, 2026, 9:44 p.m. |
| PD | Predicate disambiguation | batch_69deb97bd8bc8190b2ad4888f97cf963 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:10 a.m.