Triple
T27360486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adramyttium |
E685806
|
entity |
| Predicate | locatedOppositeIsland |
P62725
|
FINISHED |
| Object | Lesbos |
—
|
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: Lesbos | Statement: [Adramyttium, locatedOppositeIsland, Lesbos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedOppositeIsland Context triple: [Adramyttium, locatedOppositeIsland, Lesbos]
-
A.
neighboringIsland
Indicates that one island is geographically adjacent to or very close to another island, typically separated only by a narrow body of water.
-
B.
hasIslandGroupOnOtherSide
chosen
Indicates that an island group is located on the opposite side of a specified reference point or boundary relative to another entity.
-
C.
betweenIsland
Indicates a spatial relationship where something is located in the area separating two or more islands.
-
D.
locatedInArchipelago
Indicates that one place or geographic entity is situated within or is part of a specific archipelago.
-
E.
destinationIsland
Indicates the island that serves as the endpoint or target location to which someone or something is going or being directed.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69feced53a7c819098ec474fb7d514b0 |
completed | May 9, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69fecd9cd5288190aac8b4e04a7ee78e |
completed | May 9, 2026, 6:01 a.m. |
Created at: April 27, 2026, 11:53 a.m.