Triple
T6785030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frozen Four |
E155778
|
entity |
| Predicate | hasNicknamePattern |
P58262
|
FINISHED |
| Object | modeled after NCAA basketball Final Four branding |
—
|
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: modeled after NCAA basketball Final Four branding | Statement: [Frozen Four, hasNicknamePattern, modeled after NCAA basketball Final Four branding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNicknamePattern Context triple: [Frozen Four, hasNicknamePattern, modeled after NCAA basketball Final Four branding]
-
A.
hasNicknameForm
Indicates that one entity is a nickname or informal variant form of another entity’s name.
-
B.
nicknamePattern
chosen
Indicates that one entity serves as a nickname or informal name pattern for another entity.
-
C.
isNickname
Indicates that one name is an informal or alternative name commonly used to refer to the same person or entity as another name.
-
D.
hasNicknameTheme
Indicates that an entity’s nickname is based on or associated with a particular theme or motif.
-
E.
namePattern
Indicates that an entity’s name follows or matches a specified pattern or format.
- 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_69c6881770fc8190972b2906390380f5 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d28de0348190998751fd546bfd02 |
completed | March 27, 2026, 6:55 p.m. |
| PD | Predicate disambiguation | batch_69c6d0979ce0819094678896da4e3169 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:14 p.m.