Triple
T12444560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Te Anau Glowworm Caves |
E297362
|
entity |
| Predicate | tourDurationApprox |
P72407
|
FINISHED |
| Object | 2.5 hours |
—
|
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: 2.5 hours | Statement: [Te Anau Glowworm Caves, tourDurationApprox, 2.5 hours]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tourDurationApprox Context triple: [Te Anau Glowworm Caves, tourDurationApprox, 2.5 hours]
-
A.
rideDuration
Indicates the length of time that a ride or trip lasts from start to finish.
-
B.
voyageDuration
Indicates the length of time that a voyage or journey lasts from its start to its end.
-
C.
typicalTourDuration
chosen
Indicates the usual length of time that a tour normally takes to complete.
-
D.
banDurationApproximate
Indicates that the duration of a ban is known only approximately rather than as an exact, precise time period.
-
E.
travelTimeCategory
Indicates the qualitative classification of how long a given travel or trip duration is (e.g., short, medium, long).
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95151e7348190a1d4953a8b416a13 |
completed | April 10, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69d94d3c27a08190a0237200203e476d |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.