Triple
T36584850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pepsi Zero Sugar Super Bowl LI Halftime Show |
E902493
|
entity |
| Predicate | eventSegment |
P82320
|
FINISHED |
| Object | halftime |
—
|
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: halftime | Statement: [Pepsi Zero Sugar Super Bowl LI Halftime Show, eventSegment, halftime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eventSegment Context triple: [Pepsi Zero Sugar Super Bowl LI Halftime Show, eventSegment, halftime]
-
A.
eventStructure
chosen
Indicates how an event is internally organized into components such as subevents, phases, participants’ roles, and their temporal or causal relationships.
-
B.
eventLeadingTo
Indicates a causal relationship where one event brings about, triggers, or results in the occurrence of another event.
-
C.
event
Indicates that there exists an occurrence or happening involving one or more entities, typically situated in time and possibly space.
-
D.
eventIn
Indicates that an event occurs within, or is situated in, a specific location, context, or larger event.
-
E.
eventName
Indicates the specific label or title assigned to identify an event within a system or context.
- 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_69f76e64d8908190868473959a250b94 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.