Triple
T7744244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swift Run Gap entrance |
E175584
|
entity |
| Predicate | givesEntryTo |
P76727
|
FINISHED |
| Object | park visitor facilities in central Shenandoah |
—
|
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: park visitor facilities in central Shenandoah | Statement: [Swift Run Gap entrance, givesEntryTo, park visitor facilities in central Shenandoah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: givesEntryTo Context triple: [Swift Run Gap entrance, givesEntryTo, park visitor facilities in central Shenandoah]
-
A.
entersBy
chosen
Indicates that one entity moves into or gains access to another entity through a specified entrance, route, or means.
-
B.
enteredIntoBy
Indicates that an agreement, contract, or formal arrangement has been initiated or established by a particular party.
-
C.
entersFrom
Indicates that one entity moves into or arrives at a place, state, or context by coming from another specified source or location.
-
D.
givenTo
Indicates that something is transferred or presented by one entity to another as a recipient.
-
E.
enteredBy
Indicates that one entity has been input, recorded, or submitted into a system, record, or context by another entity.
- 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_69c69960b3588190a53aa590d31d9544 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c70402169481909b219dc5f4a64b9b |
completed | March 27, 2026, 10:26 p.m. |
| PD | Predicate disambiguation | batch_69c7016c4a748190a7012030edaefcee |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:07 p.m.