Triple
T17787117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louni Island |
E444045
|
entity |
| Predicate | relativeSizeWithinGroup |
P8238
|
FINISHED |
| Object | small island |
—
|
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: small island | Statement: [Louni Island, relativeSizeWithinGroup, small island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeSizeWithinGroup Context triple: [Louni Island, relativeSizeWithinGroup, small island]
-
A.
relativeSizeWithinSite
Indicates the comparative size relationship of one entity to another within the same site or local context.
-
B.
relativePositionInGroup
Indicates the spatial or ordered placement of an entity within a defined group relative to the other members of that group.
-
C.
relativeSizeInFleet
Indicates the comparative size or capacity of an entity relative to other entities within the same fleet.
-
D.
relativeSizeOnTethys
Indicates how the size of one entity compares to another specifically in the context of Tethys.
-
E.
hasRelativeSize
chosen
Indicates that one entity’s size is being compared to another entity’s size, expressing a relative rather than absolute magnitude.
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e487938418819096016ad717b014e6 |
completed | April 19, 2026, 7:43 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:12 a.m.