Triple
T37597788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hatiya Island |
E935438
|
entity |
| Predicate | mainLivelihoodSource |
P29524
|
FINISHED |
| Object | marine fishing |
—
|
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: marine fishing | Statement: [Hatiya Island, mainLivelihoodSource, marine fishing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainLivelihoodSource Context triple: [Hatiya Island, mainLivelihoodSource, marine fishing]
-
A.
livelihood
chosen
Indicates that one entity serves as the primary means of support, income, or subsistence for another entity.
-
B.
livelihoodArea
Indicates the area or domain in which an entity earns its living or sustains its means of support.
-
C.
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.
-
D.
primarySectorActivity
Indicates the main industry or sector in which an entity primarily conducts its activities or operations.
-
E.
livelihoodChallenges
Indicates difficulties or obstacles that negatively affect an entity’s ability to secure or maintain its means of living or income.
- 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.