Triple
T15654987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yanomami |
E376414
|
entity |
| Predicate | faceThreatFrom |
P43422
|
FINISHED |
| Object | illegal gold mining |
—
|
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: illegal gold mining | Statement: [Yanomami, faceThreatFrom, illegal gold mining]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: faceThreatFrom Context triple: [Yanomami, faceThreatFrom, illegal gold mining]
-
A.
facesThreat
chosen
Indicates that an entity is exposed to or confronted by a potential danger, risk, or harmful situation.
-
B.
perceivedThreat
Indicates that one entity regards another entity or situation as potentially harmful, dangerous, or adverse.
-
C.
threatFactors
Indicates that certain conditions, elements, or circumstances contribute to increasing the risk or likelihood of a harmful or adverse outcome.
-
D.
threatType
Indicates the specific category or nature of a threat that one entity poses or represents in relation to another.
-
E.
threat
Indicates a relationship where one entity expresses or poses potential harm, danger, or negative consequences toward 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_69d85cd1564c8190991adda63bfab4b0 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04ef1f83c8190bbf65eed162cbd55 |
completed | April 16, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69deda890140819082608931e993dd61 |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:15 a.m.