Triple
T20349324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devil's Snare |
E495965
|
entity |
| Predicate | reactionToLight |
P86901
|
FINISHED |
| Object | shrivels |
—
|
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: shrivels | Statement: [Devil's Snare, reactionToLight, shrivels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reactionToLight Context triple: [Devil's Snare, reactionToLight, shrivels]
-
A.
sensitivityToLight
Indicates a relationship where an entity reacts adversely or more strongly than normal when exposed to light.
-
B.
photosensitivity
chosen
Indicates a relationship where an entity reacts or responds in a particular way when exposed to light.
-
C.
glowsInPresenceOf
Indicates that one entity emits or intensifies light when another specified entity or condition is present.
-
D.
reactivity
Indicates how readily one entity undergoes a chemical or physical change in response to interaction with another entity or external conditions.
-
E.
canLight
Indicates that one entity has the ability or capacity to provide or emit light to another entity or environment.
- 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6783af5dc8190a40c3b9816cd1aef |
completed | April 20, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_69e57636b4808190bc2855af48a3ccdc |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:24 a.m.