Triple
T2227664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shandaken Tunnel |
E48689
|
entity |
| Predicate | outflowWatercourse |
P36349
|
FINISHED |
| Object | Esopus Creek watershed |
—
|
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: Esopus Creek watershed | Statement: [Shandaken Tunnel, outflowWatercourse, Esopus Creek watershed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outflowWatercourse Context triple: [Shandaken Tunnel, outflowWatercourse, Esopus Creek watershed]
-
A.
mouthOfTheWatercourse
Indicates the location where a watercourse ends and flows into a larger body of water.
-
B.
hasWatercourseType
Indicates the specific kind or category of watercourse (such as river, stream, or canal) associated with an entity.
-
C.
watercourseName
Indicates the name assigned to a river, stream, or other flowing body of water in the relationship.
-
D.
mouthOfWatercourse
Indicates the location where a watercourse ends and flows into a larger body of water or another watercourse.
-
E.
sourceOfWatercourse
Indicates that one entity is the origin or starting point from which a watercourse (such as a river or stream) begins or flows.
- F. None of above. chosen
Provenance (4 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_69a88aa51b388190949868ec9766e587 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc0670ce48190b98814064bff0517 |
completed | March 7, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69abbdadbb0c8190b3a1ede31b8acbfa |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbe4252688190944491a450383450 |
completed | March 7, 2026, 5:57 a.m. |
Created at: March 4, 2026, 7:47 p.m.