Triple
T3303723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thursday Night Football |
E69396
|
entity |
| Predicate | broadcastOnDay |
P14563
|
FINISHED |
| Object | Thursday |
—
|
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: Thursday | Statement: [Thursday Night Football, broadcastOnDay, Thursday]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: broadcastOnDay Context triple: [Thursday Night Football, broadcastOnDay, Thursday]
-
A.
broadcastDay
chosen
Indicates the specific day on which a program, event, or content is broadcast or scheduled to be broadcast.
-
B.
broadcastDuring
Indicates that one event or program is broadcast while another specified time period or event is occurring.
-
C.
broadcastFor
Indicates that one entity transmits or disseminates content, information, or a signal on behalf of, or in service of, another entity.
-
D.
broadcastVia
Indicates that an action, message, or content is transmitted or disseminated through a specified medium, channel, or platform.
-
E.
broadcastFrom
Indicates that some content, signal, or message is transmitted or emitted starting at a particular source location, device, or entity.
- 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_69ad859f218081909458d2cebbf57565 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0c662308190aad8b2a93e1c8a5c |
completed | March 8, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_69ada42625308190be257f16a623a410 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:11 p.m.