Triple
T12097809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moai statues |
E288114
|
entity |
| Predicate | typicalLocationOnIsland |
P16601
|
FINISHED |
| Object | ahu (ceremonial stone platforms) |
—
|
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: ahu (ceremonial stone platforms) | Statement: [Moai statues, typicalLocationOnIsland, ahu (ceremonial stone platforms)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalLocationOnIsland Context triple: [Moai statues, typicalLocationOnIsland, ahu (ceremonial stone platforms)]
-
A.
foundOnIsland
Indicates that one entity is located or discovered on an island in relation to another entity.
-
B.
locatedInRegionOfIsland
Indicates that an entity is situated within a specific region that is part of an island.
-
C.
relativeLocationOnIsland
chosen
Indicates a spatial relationship where one entity’s position is described relative to another entity specifically in the context of being on an island.
-
D.
meetsInIsland
Indicates that two or more entities meet with each other at a location that is an island.
-
E.
hasIslandNearby
Indicates that one location is situated close to an island in geographic space.
- 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_69d6ab4964708190850585628b287b0c |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9178ad99c8190a54777b9bbe998bc |
completed | April 10, 2026, 3:30 p.m. |
| PD | Predicate disambiguation | batch_69d915000454819089fee00022055599 |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:48 p.m.