Triple
T2909617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wisconsin glaciation |
E63649
|
entity |
| Predicate | endApproximate |
P8204
|
FINISHED |
| Object | about 11,000 years ago |
—
|
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: about 11,000 years ago | Statement: [Wisconsin glaciation, endApproximate, about 11,000 years ago]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endApproximate Context triple: [Wisconsin glaciation, endApproximate, about 11,000 years ago]
-
A.
timePeriodEndApprox
Indicates that the associated time period ends at an approximate, rather than exact, point in time.
-
B.
hasApproximateEnd
chosen
Indicates that an entity’s end point, time, or boundary is known only approximately rather than precisely.
-
C.
endTimeApproximate
Indicates that the recorded end time of an event or action is not exact but an approximate value.
-
D.
approximateEndUse
Indicates that something is an estimated or inferred final purpose, application, or consumption context of another entity.
-
E.
endDate
Indicates the point in time at which an event, state, or relationship stops being valid or comes to a conclusion.
- 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_69ab4c44ab448190b9411324e8a1fc1d |
completed | March 6, 2026, 9:51 p.m. |
| NER | Named-entity recognition | batch_69abe0d329c88190b6fcaef0be1799eb |
completed | March 7, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69abdd1b77608190b20fc078fdb85e64 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:11 p.m.