Triple
T27727187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | lighthouse at Laem Tanod |
E697331
|
entity |
| Predicate | locatedInNationalParkZone |
P9791
|
FINISHED |
| Object | Mu Ko Lanta terrestrial area |
—
|
NE NERFINISHED |
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: Mu Ko Lanta terrestrial area | Statement: [lighthouse at Laem Tanod, locatedInNationalParkZone, Mu Ko Lanta terrestrial area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInNationalParkZone Context triple: [lighthouse at Laem Tanod, locatedInNationalParkZone, Mu Ko Lanta terrestrial area]
-
A.
withinNationalPark
chosen
Indicates that one entity is located inside the geographic boundaries of a national park designated by another entity.
-
B.
locatedInNationalParkOrQuasiNationalPark
Indicates that something is situated within the boundaries of a national park or a quasi-national park.
-
C.
locatedInNationalOrProvincialPark
Indicates that one entity is situated within the boundaries of a national or provincial park.
-
D.
locatedNearNationalPark
Indicates that one place or entity is situated in close proximity to a national park.
-
E.
locatedInNationalLakeshore
Indicates that one place or feature is situated within the boundaries of a designated national lakeshore area.
- 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_69ef590c3e288190ad54d2465af8ca4e |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69ff1a972bf08190860696ffcd887c0f |
completed | May 9, 2026, 11:29 a.m. |
| PD | Predicate disambiguation | batch_69ff184005d88190bf38283ebc499b28 |
completed | May 9, 2026, 11:19 a.m. |
Created at: April 27, 2026, 3:10 p.m.