Triple
T12069194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harris Interactive Poll |
E287376
|
entity |
| Predicate | pollFrequency |
P97314
|
FINISHED |
| Object | weekly during the college football season |
—
|
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: weekly during the college football season | Statement: [Harris Interactive Poll, pollFrequency, weekly during the college football season]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pollFrequency Context triple: [Harris Interactive Poll, pollFrequency, weekly during the college football season]
-
A.
broadcastFrequency
Indicates the specific radio or transmission frequency at which a broadcast is sent or received.
-
B.
measurementFrequency
Indicates how often a measurement is taken or recorded over time.
-
C.
inspectionFrequency
Indicates how often an entity is examined, checked, or reviewed within a given time period.
-
D.
rankingUpdateFrequency
Indicates how often the ranking or ordered list associated with an entity is recalculated or refreshed.
-
E.
surveyCadence
chosen
Indicates how frequently or at what regular interval surveys are conducted or sent out.
- 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_69d6ab4846e081908ee7bbd66a6d3459 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bda47c8190b94860b31df4a98c |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:48 p.m.