Triple
T33762033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kitsis/Horowitz |
E865133
|
entity |
| Predicate | occupationOfFounder |
P177833
|
FINISHED |
| Object | television writer |
—
|
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: television writer | Statement: [Kitsis/Horowitz, occupationOfFounder, television writer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occupationOfFounder Context triple: [Kitsis/Horowitz, occupationOfFounder, television writer]
-
A.
founderNationality
Indicates that the specified person’s country of origin or citizenship is the one associated with the founder in question.
-
B.
founderBirthPlace
Indicates the place where the founder of an entity was born.
-
C.
founderKnownFor
Indicates that a founder is particularly recognized or notable for a specific work, achievement, product, or contribution.
-
D.
foundedByCitizenOf
Indicates that an entity (such as an organization, institution, or settlement) was established by a founder who is a citizen of a specified country or state.
-
E.
ownerAtFounding
Indicates that an entity is the owner of another entity at the time the latter is founded or established.
- 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_69f3498d3b748190aa3c4006c1f32f38 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7051ad6e4819095e82bbd64761803 |
completed | May 3, 2026, 8:19 a.m. |
| PD | Predicate disambiguation | batch_69f700fe24e08190998e2c96fbaaad38 |
completed | May 3, 2026, 8:02 a.m. |
| PDg | Predicate description generation | batch_69f70519f114819080659840c04d7911 |
completed | May 3, 2026, 8:19 a.m. |
Created at: May 1, 2026, 1:45 a.m.