Triple
T19812246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halahala poison |
E475974
|
entity |
| Predicate | resultOfConsumption |
P86018
|
FINISHED |
| Object | Shiva’s throat turning blue |
—
|
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: Shiva’s throat turning blue | Statement: [Halahala poison, resultOfConsumption, Shiva’s throat turning blue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultOfConsumption Context triple: [Halahala poison, resultOfConsumption, Shiva’s throat turning blue]
-
A.
consumes
Indicates that one entity eats, drinks, or otherwise uses up another entity as a resource or nourishment.
-
B.
consequenceOfFood
chosen
Indicates a result, effect, or outcome that occurs because of a particular food or food-related action.
-
C.
isConsumedIn
Indicates that one entity is used up, ingested, or otherwise expended as part of a process, event, or action involving another entity.
-
D.
consumptionMethod
Indicates the manner or process by which something is consumed, used up, or ingested.
-
E.
largelyConsumedBy
Indicates that something is mostly or predominantly eaten or used up by a particular consumer or group.
- 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_69d8e51bc4208190a1c57d8c5d1b15e4 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6542c9c5c81908772e88caa067e63 |
completed | April 20, 2026, 4:28 p.m. |
| PD | Predicate disambiguation | batch_69e5305858108190bbbfdb9ba3ab9f80 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:50 p.m.