Triple
T28793236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coreguaje people |
E727014
|
entity |
| Predicate | relationToForest |
P128550
|
FINISHED |
| Object | forest-dependent livelihoods |
—
|
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: forest-dependent livelihoods | Statement: [Coreguaje people, relationToForest, forest-dependent livelihoods]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationToForest Context triple: [Coreguaje people, relationToForest, forest-dependent livelihoods]
-
A.
relatedRoot
Indicates that one entity is connected to another through a shared or common root, origin, or foundational source.
-
B.
hasForestAssociation
chosen
Indicates an ecological or contextual relationship in which an entity is associated with, influenced by, or characteristically occurs in forest environments.
-
C.
structureRelation
Indicates a structural relationship between entities, specifying how one entity is organized, arranged, or connected in relation to another.
-
D.
relationToSource
Indicates a relationship that specifies how something is connected or related to its originating source.
-
E.
allyRelation
Indicates a cooperative, supportive relationship in which the entities act as allies toward shared or aligned goals.
- 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_69f0319b7c44819085736bcc256185e6 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_6a0079e152648190a9da2add94fc1831 |
completed | May 10, 2026, 12:28 p.m. |
| PD | Predicate disambiguation | batch_6a0078f77f9c8190af357a6016a2bd53 |
completed | May 10, 2026, 12:24 p.m. |
Created at: April 28, 2026, 6:24 a.m.