Triple
T31743502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sari, Papua New Guinea |
E810201
|
entity |
| Predicate | foodSecurityStrategy |
P134387
|
FINISHED |
| Object | subsistence production with limited market sales |
—
|
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: subsistence production with limited market sales | Statement: [Sari, Papua New Guinea, foodSecurityStrategy, subsistence production with limited market sales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foodSecurityStrategy Context triple: [Sari, Papua New Guinea, foodSecurityStrategy, subsistence production with limited market sales]
-
A.
foodPolicy
chosen
Indicates the rules, guidelines, or strategies that govern how food is produced, distributed, sold, or consumed within a given context.
-
B.
dailyRationPlanning
Indicates the planning or allocation of daily rations or supplies for entities.
-
C.
foodRationLevel
Indicates the quantity or adequacy of food allocated to an entity over a given period.
-
D.
foodRationingInHostCountry
Indicates that the host country imposes restrictions or controlled distribution on available food supplies.
-
E.
foodSources
Indicates a relationship where one entity serves as a source of food or nourishment for 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_69f348e233cc819083b6695f70cd75d8 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6ab4c16e08190ae522564534d243d |
completed | May 3, 2026, 1:56 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:25 p.m.