Triple
T38079720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SEC Western Division vs SEC Eastern Division |
E950817
|
entity |
| Predicate | typicalScheduleFrequency |
P128659
|
FINISHED |
| Object | annual meetings between divisions |
—
|
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: annual meetings between divisions | Statement: [SEC Western Division vs SEC Eastern Division, typicalScheduleFrequency, annual meetings between divisions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalScheduleFrequency Context triple: [SEC Western Division vs SEC Eastern Division, typicalScheduleFrequency, annual meetings between divisions]
-
A.
typicalSchedule
Indicates the usual or standard timing and sequence of activities or events associated with an entity.
-
B.
typicalPeriod
Indicates the usual or characteristic time interval or duration associated with an event, process, or state.
-
C.
serviceFrequencyType
Indicates how often a service occurs or is scheduled within a given time period.
-
D.
typicalUpdateFrequency
Indicates how often an entity is usually updated or refreshed over time.
-
E.
schedulePattern
chosen
Indicates a recurring or structured timing relationship that defines when an event or action is scheduled to occur.
- 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_69f76f02a6c48190a94f3c0b3ee90cf2 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037df1223c8190a5d61e4f8e6fd613 |
completed | May 12, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_6a037a1ad6c48190bfe35d350c1b4751 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:21 p.m.