Triple
T10543808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irrawaddy Delta |
E248761
|
entity |
| Predicate | supportsLivelihood |
P29524
|
FINISHED |
| Object | smallholder farmers |
—
|
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: smallholder farmers | Statement: [Irrawaddy Delta, supportsLivelihood, smallholder farmers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsLivelihood Context triple: [Irrawaddy Delta, supportsLivelihood, smallholder farmers]
-
A.
livelihood
chosen
Indicates that one entity serves as the primary means of support, income, or subsistence for another entity.
-
B.
livelihoodChange
Indicates a change in a person’s or group’s means of making a living, such as improvements, declines, or shifts in income-generating activities.
-
C.
supportsLife
Indicates that one entity provides conditions or resources that allow another entity to live, grow, or remain biologically viable.
-
D.
livelihoodVulnerability
Indicates the degree to which an entity’s means of making a living are exposed or susceptible to harm, disruption, or loss.
-
E.
supportedFamilyLifeOf
Indicates that one entity provided assistance or resources that helped sustain or improve the family life or family-related well-being of 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d51911b10481909e6e548879e8de36 |
completed | April 7, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69d4fb9729288190a0149f127acd7ae3 |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:32 p.m.