Triple
T38178842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poiqu River |
E1000295
|
entity |
| Predicate | transitionsNameTo |
P157853
|
FINISHED |
| Object | Bhote Koshi River |
—
|
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: Bhote Koshi River | Statement: [Poiqu River, transitionsNameTo, Bhote Koshi River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transitionsNameTo Context triple: [Poiqu River, transitionsNameTo, Bhote Koshi River]
-
A.
changesNameTo
chosen
Indicates that an entity alters its current name and adopts a new specified name.
-
B.
conversionName
Indicates that one entity is the name or label assigned to a specific conversion event or conversion process associated with another entity.
-
C.
marksLabelTransitionTo
Indicates that something designates or signals the point at which one label changes or transitions to another label.
-
D.
dstTransitionBasis
Indicates the rule, event, or condition that serves as the basis for transitioning from standard time to daylight saving time (or vice versa).
-
E.
translatedFromName
Indicates that one entity is a translated version of another entity’s name.
- 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_69f76daaace48190a38cee37f8ce343f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69ffed8912488190baa05f572e5b1b89 |
completed | May 10, 2026, 2:29 a.m. |
| PD | Predicate disambiguation | batch_69ffed12a76c8190ad85c6ac869c72e9 |
completed | May 10, 2026, 2:27 a.m. |
Created at: May 3, 2026, 4:29 p.m.