Triple
T29117609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mattress Firm Amphitheatre |
E737089
|
entity |
| Predicate | hasCorporateNamingRightsSponsor |
P3318
|
FINISHED |
| Object | Mattress Firm |
—
|
NE NERFINISHED |
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: Mattress Firm | Statement: [Mattress Firm Amphitheatre, hasCorporateNamingRightsSponsor, Mattress Firm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCorporateNamingRightsSponsor Context triple: [Mattress Firm Amphitheatre, hasCorporateNamingRightsSponsor, Mattress Firm]
-
A.
namingRightsBrand
Indicates that a brand holds the official naming rights for a venue, event, or property.
-
B.
namingRightsCity
Indicates that a city holds the naming rights associated with a particular entity, venue, or event.
-
C.
ballparkNameSponsor
Indicates that a particular sponsor is the naming-rights sponsor for a ballpark.
-
D.
namingRightsHolder
chosen
Indicates which entity holds the official right to name or brand another entity (such as a venue, event, or asset).
-
E.
sponsorOfStadiumName
Indicates that an entity serves as the naming-rights sponsor for a particular stadium.
- 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_69f077ed54e08190bb02a744e8121a66 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a003f6083608190a5deadc7291cf70e |
completed | May 10, 2026, 8:18 a.m. |
| PD | Predicate disambiguation | batch_6a003c935c40819085fdb255a52ba03b |
completed | May 10, 2026, 8:06 a.m. |
Created at: April 28, 2026, 11:23 a.m.