Triple
T26538097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Party Pieces |
E671304
|
entity |
| Predicate | hasFounderRelationship |
P172773
|
FINISHED |
| Object | Middleton family business |
—
|
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: Middleton family business | Statement: [Party Pieces, hasFounderRelationship, Middleton family business]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFounderRelationship Context triple: [Party Pieces, hasFounderRelationship, Middleton family business]
-
A.
hasParentCompanyFounder
Indicates that an entity is the founder of the parent company of another entity.
-
B.
hasCoFounderRoleOf
Indicates that one entity holds the role or position of co-founder in relation to another entity, such as an organization or venture.
-
C.
hasFounderPreviousAffiliation
Indicates that a founder of an entity was previously affiliated (e.g., employed, enrolled, or otherwise formally associated) with another organization or institution.
-
D.
hasFounderName
Indicates that an entity has a founder whose personal name is given by the associated value.
-
E.
founderAlsoOwns
Indicates that the person or entity who founded something also retains ownership of it.
- F. None of above. chosen
Provenance (4 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_69eeb3206e748190b90c85cc81f38c91 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f6b0d21dd08190a9883ff71c94c71c |
completed | May 3, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
| PDg | Predicate description generation | batch_69f6afeaaef88190aefa97e83f8db906 |
completed | May 3, 2026, 2:16 a.m. |
Created at: April 27, 2026, 1:39 a.m.