Triple
T32076351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union Glacier |
E819164
|
entity |
| Predicate | typicalOperatingMonths |
P93895
|
FINISHED |
| Object | November |
—
|
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: November | Statement: [Union Glacier, typicalOperatingMonths, November]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalOperatingMonths Context triple: [Union Glacier, typicalOperatingMonths, November]
-
A.
operatingMonthsApproximate
Indicates that the time period during which something operates is specified in approximate months rather than exact dates.
-
B.
typicalContractMonths
Indicates the usual or standard number of months that a contract is expected to run.
-
C.
operationalPeriodApprox
Indicates that the time span during which something was in operation is known only approximately rather than as an exact period.
-
D.
operatedSeasonallyFrom
Indicates that an entity was in operation only during specific seasons or periods within a given timeframe.
-
E.
typicallyOpenFromMonth
chosen
Indicates the month from which something (such as a place, service, or facility) is usually open or begins operating.
- 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_69f348ff8ef88190931c08ba530a36bc |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379eaa540819095a1c5d9f3513f9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 12:23 a.m.