Triple
T14536025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donkey’s Christmas Shrektacular |
E341044
|
entity |
| Predicate | usesFranchiseStyle |
P40406
|
FINISHED |
| Object | Shrek humor |
—
|
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: Shrek humor | Statement: [Donkey’s Christmas Shrektacular, usesFranchiseStyle, Shrek humor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesFranchiseStyle Context triple: [Donkey’s Christmas Shrektacular, usesFranchiseStyle, Shrek humor]
-
A.
usedByFranchise
Indicates that something (such as a resource, asset, or element) is utilized or employed by a particular franchise.
-
B.
supportsFranchise
Indicates that one entity provides backing, resources, or endorsement to help establish, maintain, or promote a franchise associated with another entity.
-
C.
franchiseOf
Indicates that one entity operates as a franchise belonging to or licensed by another entity.
-
D.
usesHouseStyle
chosen
Indicates that one entity follows or applies the specific house style (a defined set of stylistic or formatting conventions) associated with another entity.
-
E.
supportsFranchiseType
Indicates that one entity is compatible with, or provides the necessary capabilities for, a particular type of franchise.
- 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_69d822dac79c8190a84a073f3cbaced5 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb1b9d39881908c7a3a5b17d432af |
completed | April 14, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69de5c546c7081909e27d504ec360c5c |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:22 a.m.