Triple
T28242150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basilan Island |
E712055
|
entity |
| Predicate | locatedOnSeaLane |
P56308
|
FINISHED |
| Object | Sulu Archipelago sea routes |
—
|
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: Sulu Archipelago sea routes | Statement: [Basilan Island, locatedOnSeaLane, Sulu Archipelago sea routes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedOnSeaLane Context triple: [Basilan Island, locatedOnSeaLane, Sulu Archipelago sea routes]
-
A.
locatedAlong
Indicates that one entity is situated adjacent to, or running beside, the length or course of another linear feature (such as a road, river, or railway).
-
B.
nearbySeaLane
chosen
Indicates that one entity is located close to a sea lane used for maritime navigation or shipping.
-
C.
locatedOnRouteTo
Indicates that one entity lies along the path or course taken when traveling from a starting point to a specified destination.
-
D.
locatedAtSea
Indicates that something exists or is situated in or on the sea.
-
E.
locatedOnLoop
Indicates that an entity is situated along or directly on a loop-shaped path, route, or circuit.
- 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_69efb51fb98881909692421959ec0170 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69ff5b233e9c8190adc06cca0758986b |
completed | May 9, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69ff5a5682108190a006b23c4fcdcc7c |
completed | May 9, 2026, 4:01 p.m. |
Created at: April 27, 2026, 10:59 p.m.