Triple
T29554197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Australia and Indonesia |
E749860
|
entity |
| Predicate | areNeighborsAcross |
P138389
|
FINISHED |
| Object | Timor Sea |
—
|
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: Timor Sea | Statement: [Australia and Indonesia, areNeighborsAcross, Timor Sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: areNeighborsAcross Context triple: [Australia and Indonesia, areNeighborsAcross, Timor Sea]
-
A.
isAdjacentTo
Indicates that one entity is directly next to or bordering another without anything of the same type in between.
-
B.
neighboringTo
Indicates that one entity is located directly adjacent or very close to another entity, sharing a common boundary or immediate vicinity.
-
C.
hasNeighborAcrossFjord
chosen
Indicates that one entity is located across a fjord from another entity, such that they are neighbors separated by the fjord.
-
D.
isCrossBetween
Indicates that one entity is a hybrid or intermediate form resulting from the combination or mixing of two other entities.
-
E.
hasNeighborRelationshipWith
Indicates that one entity is located adjacent to or directly next to another entity, sharing a neighbor relationship.
- 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_69f0bd4919e48190942b2a13d5b97d03 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66cf946f881909d177507a28a657b |
completed | May 2, 2026, 9:30 p.m. |
| PD | Predicate disambiguation | batch_69f6633ac8a88190ab0cda62bbfcf9b0 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 5:14 p.m.