Triple
T36125918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shopping Spree (game show) |
E1044879
|
entity |
| Predicate | contestantStructure |
P82094
|
FINISHED |
| Object | teams of contestants |
—
|
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: teams of contestants | Statement: [Shopping Spree (game show), contestantStructure, teams of contestants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contestantStructure Context triple: [Shopping Spree (game show), contestantStructure, teams of contestants]
-
A.
featuresContestants
chosen
Indicates that something (such as an event, show, or competition) includes or presents certain individuals as contestants.
-
B.
featuresContestantsFrom
Indicates that something, typically a show or event, includes contestants originating from a specified source or group.
-
C.
contestantFullName
Indicates that the relationship specifies the complete, properly ordered name of a contestant.
-
D.
featuresContestantSelectionBy
Indicates that something includes or presents a contestant selection process carried out by a specified agent or entity.
-
E.
contestantOn
Indicates that one entity participates as a competitor in a contest, show, or competition associated with another 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_69f76e356c908190abc6ca1e6a05b011 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:08 p.m.