Triple
T27409451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kei people |
E692100
|
entity |
| Predicate | hasCustomaryMarineTenureSystem |
P126319
|
FINISHED |
| Object | sasi |
—
|
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: sasi | Statement: [Kei people, hasCustomaryMarineTenureSystem, sasi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCustomaryMarineTenureSystem Context triple: [Kei people, hasCustomaryMarineTenureSystem, sasi]
-
A.
hasMarineManagement
Indicates that an entity exercises authority or responsibility over the planning, regulation, or stewardship of marine areas or resources.
-
B.
hasMarineStatus
Indicates that an entity possesses a specific classification or condition related to its status in a marine or oceanic context.
-
C.
hasMarineReserve
Indicates that an entity possesses, includes, or is associated with a designated marine reserve area.
-
D.
hasCustomaryAuthority
chosen
Indicates that one entity holds traditionally recognized or socially accepted power, control, or decision-making authority over another entity or domain.
-
E.
hasMarineResource
Indicates that one entity possesses, contains, or is associated with a marine (ocean or sea-based) resource in relation to another entity.
- 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_69ef5205fc808190ad3efc5525b8e6d6 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 27, 2026, 12:31 p.m.