Triple
T28996841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MIThenge |
E736187
|
entity |
| Predicate | hasApproximateTimeOfDay |
P6019
|
FINISHED |
| Object | sunset |
—
|
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: sunset | Statement: [MIThenge, hasApproximateTimeOfDay, sunset]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateTimeOfDay Context triple: [MIThenge, hasApproximateTimeOfDay, sunset]
-
A.
hasTimeOfDay
chosen
Indicates that a situation, event, or state occurs during, or is associated with, a specific part of the day (e.g., morning, afternoon, evening, night).
-
B.
hasApproximateDuration
Indicates that one entity has a duration that is estimated or not exact, typically expressed as an approximate length of time.
-
C.
approximateTimeOfDayOfEventCommemorated
Indicates the general time of day during which the commemorated event is understood to have occurred.
-
D.
timeStartApprox
Indicates that the associated event or state begins at an approximate, rather than exact, point in time.
-
E.
hasTimeOffset
Indicates that one temporal value is shifted or displaced from another by a specified amount of time.
- 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_69f077eacd0481908ef0bafd74491cd0 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f7886be6d8819095ec62e4f2cee858 |
completed | May 3, 2026, 5:39 p.m. |
| PD | Predicate disambiguation | batch_69f7841440f48190b4346c08855951d2 |
completed | May 3, 2026, 5:21 p.m. |
Created at: April 28, 2026, 9:31 a.m.