Triple
T618062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sentinelese |
E14448
|
entity |
| Predicate | riskFromContact |
P3842
|
FINISHED |
| Object | high susceptibility to disease |
—
|
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: high susceptibility to disease | Statement: [Sentinelese, riskFromContact, high susceptibility to disease]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riskFromContact Context triple: [Sentinelese, riskFromContact, high susceptibility to disease]
-
A.
riskType
Indicates the category or nature of risk associated with an entity, event, or relationship.
-
B.
riskLevel
chosen
Indicates the degree of potential harm, loss, or adverse outcome associated with a particular situation, action, or entity.
-
C.
riskFeature
Indicates that one entity possesses or exhibits a characteristic, condition, or attribute that increases the likelihood or severity of a negative outcome for another entity or situation.
-
D.
historicalContactWith
Indicates that two entities have interacted or been in communication with each other at some point in the past.
-
E.
risk
Indicates that one entity is exposed or subject to potential harm, loss, or adverse outcome arising from another entity, action, or situation.
- 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e2418c881908552d2c4a5006e97 |
completed | March 1, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69a49cfd15288190b4abdbd0bce3edcd |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.