Triple
T23149686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kohelepelepe |
E578287
|
entity |
| Predicate | trailFeature |
P1777
|
FINISHED |
| Object | abandoned military railway ties used as steps |
—
|
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: abandoned military railway ties used as steps | Statement: [Kohelepelepe, trailFeature, abandoned military railway ties used as steps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trailFeature Context triple: [Kohelepelepe, trailFeature, abandoned military railway ties used as steps]
-
A.
trailName
Indicates the name assigned to a specific trail or path in the relationship.
-
B.
trailAccess
Indicates that one entity provides permission or a route for another entity to enter, use, or traverse a specific trail or pathway.
-
C.
trackFeature
Indicates that one entity monitors, records, or follows the behavior, state, or evolution of a particular feature associated with another entity.
-
D.
roadFeature
chosen
Indicates that an entity is a specific physical or functional characteristic associated with a road, such as its structure, markings, or related infrastructure.
-
E.
trailDesignation
Indicates that a particular label, name, or classification has been assigned to a trail to identify its route, type, or official status.
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ed0b76c8190ac61b949d88e9970 |
completed | April 29, 2026, 4:53 a.m. |
| PD | Predicate disambiguation | batch_69ef89f83b108190aaaa1db6221fc163 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:01 p.m.