Triple
T35790500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phoenix Lights |
E1034679
|
entity |
| Predicate | eyewitnessReportsInclude |
P114231
|
FINISHED |
| Object | large silent craft |
—
|
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: large silent craft | Statement: [Phoenix Lights, eyewitnessReportsInclude, large silent craft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eyewitnessReportsInclude Context triple: [Phoenix Lights, eyewitnessReportsInclude, large silent craft]
-
A.
witnesses
Indicates that one entity observes an event, action, or situation involving another entity, typically as a bystander or observer.
-
B.
apparitionsWitnessedBy
Indicates that one entity is an apparition or ghostly phenomenon that has been seen or experienced by another entity.
-
C.
apparitionWitnessCount
Indicates the number of distinct observers who witnessed a particular apparition event.
-
D.
possibleSightings
chosen
Indicates that there are reported or potential observations of one entity by another or at a particular place or time.
-
E.
survivingWitness
Indicates that an entity is a witness to an event or situation and is still alive after it occurred.
- 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_69f76e1575908190aaa306d843b41c14 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a22e0ff88190989a5df84fca968b |
completed | May 3, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:06 p.m.