Triple
T20641338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caves of Han |
E507231
|
entity |
| Predicate | undergroundRiver |
P86882
|
FINISHED |
| Object | Lesse 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: Lesse River | Statement: [Caves of Han, undergroundRiver, Lesse River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: undergroundRiver Context triple: [Caves of Han, undergroundRiver, Lesse River]
-
A.
undergroundRiverLength
Indicates the measured linear extent of an underground river from its starting point to its endpoint.
-
B.
otherUnderworldRivers
Indicates that there exist additional rivers associated with the underworld beyond the primary or most commonly known ones.
-
C.
subterranean
Indicates that one entity is located beneath the surface of the ground or under another structure or area.
-
D.
isWatercourseOf
chosen
Indicates that a watercourse (such as a river or stream) flows through, belongs to, or is geographically associated with a particular area or feature.
-
E.
riverbedDivertedTo
Indicates that the natural course of a riverbed has been redirected or channeled toward another location or pathway.
- 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_69e0b4be702c8190a3d2410a881d310a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6af1b9e888190b61edffea16487d7 |
completed | April 20, 2026, 10:56 p.m. |
| PD | Predicate disambiguation | batch_69e5c0315f5081908098707c6455e56e |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 11:43 a.m.