Triple
T13350040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1997 Phoenix Lights |
E318045
|
entity |
| Predicate | hasReportedDuration |
P57137
|
FINISHED |
| Object | several hours |
—
|
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: several hours | Statement: [1997 Phoenix Lights, hasReportedDuration, several hours]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReportedDuration Context triple: [1997 Phoenix Lights, hasReportedDuration, several hours]
-
A.
hasDurationType
Indicates that something is associated with a specific kind or category of duration (e.g., temporary, permanent, short-term, long-term).
-
B.
hasOfficialDuration
Indicates the formally defined length of time associated with an event, process, or entity.
-
C.
hasAllegedDuration
chosen
Indicates that a specified length of time is claimed or reported for something, but not confirmed as factual.
-
D.
hasAllocatedTime
Indicates that a specific amount or period of time has been reserved or assigned for a particular entity, task, or activity.
-
E.
hasTrailDuration
Indicates that an entity (such as a trail or route) is associated with a specific amount of time required to traverse or complete it.
- 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e8c2f1c819094f0970f35f18afa |
completed | April 11, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69d98f6e53d88190bd6aa42f69b10ffb |
completed | April 11, 2026, 12:01 a.m. |
Created at: April 9, 2026, 9:31 p.m.