Triple
T1703731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Velarium |
E36822
|
entity |
| Predicate | controlledExposureTo |
P15885
|
FINISHED |
| Object | sunlight |
—
|
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: sunlight | Statement: [Velarium, controlledExposureTo, sunlight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlledExposureTo Context triple: [Velarium, controlledExposureTo, sunlight]
-
A.
controlled
Indicates that one entity has power, authority, or influence to direct, regulate, or determine the behavior, actions, or state of another entity.
-
B.
exposureType
chosen
Indicates the specific manner or context in which one entity is exposed to another entity, condition, or influence.
-
C.
controlledAfter
Indicates that one entity gains or maintains control over another entity only after a specified time, event, or condition has occurred.
-
D.
exposed
Indicates that one entity has been made visible, revealed, or left unprotected to another entity or to some external influence.
-
E.
exposes
Indicates making something visible, known, or vulnerable by removing cover, concealment, or protection.
- 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_69a88617439c819094ffb5d16a0f6307 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab75ad24408190814069e6e3ef9e59 |
completed | March 7, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69aa61bad17c8190861b92cfb423f68f |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.