Triple
T25297403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gyeyang Mountain |
E634252
|
entity |
| Predicate | averageHikingTime |
P32784
|
FINISHED |
| Object | about 1 to 2 hours round trip |
—
|
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: about 1 to 2 hours round trip | Statement: [Gyeyang Mountain, averageHikingTime, about 1 to 2 hours round trip]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: averageHikingTime Context triple: [Gyeyang Mountain, averageHikingTime, about 1 to 2 hours round trip]
-
A.
recommendedTimeToHike
Indicates the suggested or optimal time period during which one should undertake a particular hike.
-
B.
approximateHikeTimeRoundTrip
chosen
Indicates the estimated total time required to complete a hike from the starting point to the destination and back to the start.
-
C.
hikeLength
Indicates the distance or duration associated with a hiking activity or trail.
-
D.
durationTypicalAscent
Indicates the typical amount of time required to complete an ascent.
-
E.
hasClimbingTime
Indicates the duration or specific time period during which a climbing activity takes place or is allocated.
- 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_69e75a9503d48190b80a005c6af0cb50 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48fd448988190a93d953ff6e06871 |
completed | May 1, 2026, 11:34 a.m. |
| PD | Predicate disambiguation | batch_69f45d06d0388190b36ecde92013624a |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 21, 2026, 1:22 p.m.