Triple
T27265121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kulina people |
E687878
|
entity |
| Predicate | haveKnowledge |
P22660
|
FINISHED |
| Object | forest ecology |
—
|
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 ecology | Statement: [Kulina people, haveKnowledge, forest ecology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveKnowledge Context triple: [Kulina people, haveKnowledge, forest ecology]
-
A.
usesKnowledgeOf
Indicates that one entity applies or draws upon the knowledge possessed by another entity in performing an action or achieving a result.
-
B.
knows
chosen
Indicates that one entity has knowledge or awareness of another entity or piece of information.
-
C.
haveKnowledgeSystem
Indicates that an entity possesses or maintains a structured system for organizing, storing, and accessing knowledge.
-
D.
usesKnowledgeBase
Indicates that an entity consults or relies on a structured knowledge base as a source of information to perform its actions or make decisions.
-
E.
knowledgeType
Indicates the specific category or nature of knowledge associated with an entity or statement (e.g., factual, procedural, conceptual).
- 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_69ef3557abc481908bf3c146f0f3356a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f626f2c8008190b1e24ed5d521eaa3 |
completed | May 2, 2026, 4:31 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 10:55 a.m.