Triple
T2112970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Year’s Eve |
E42544
|
entity |
| Predicate | culminatesAt |
P2818
|
FINISHED |
| Object | midnight |
—
|
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: midnight | Statement: [New Year’s Eve, culminatesAt, midnight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: culminatesAt Context triple: [New Year’s Eve, culminatesAt, midnight]
-
A.
concludedAt
chosen
Indicates the point in time at which an event, process, or relationship comes to an end or is completed.
-
B.
concludedDuring
Indicates that an event, process, or state ended within the temporal bounds of another specified time period or event.
-
C.
concludedBy
Indicates that an event, process, or state is brought to an end or finalized by a specific agent or entity.
-
D.
concludedAfter
Indicates that one event or process finishes at a time later than the completion of another event or process.
-
E.
concludes
Indicates that one entity brings something (such as an event, process, or discussion) to an end or reaches a final decision or judgment about 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_69a8871040f08190aac2e2d0ab6b47ad |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbb0495d0819097dc936540743b74 |
completed | March 7, 2026, 5:43 a.m. |
| PD | Predicate disambiguation | batch_69abb7ba08948190a3c236bb53ee4257 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.