Triple
T30243317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig's Wife |
E768980
|
entity |
| Predicate | isInTheCanonOf |
P62601
|
FINISHED |
| Object | American drama |
—
|
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: American drama | Statement: [Craig's Wife, isInTheCanonOf, American drama]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInTheCanonOf Context triple: [Craig's Wife, isInTheCanonOf, American drama]
-
A.
hasPlaceInCanon
chosen
Indicates that something holds a specific status or position within an established canon or authoritative body of works.
-
B.
eraInCanon
Indicates that a subject belongs to, occurs within, or is classified as part of a specific era defined in a canon or fictional continuity.
-
C.
notInCanonOf
Indicates that something is excluded from, or does not belong to, the officially recognized canon of a given work or universe.
-
D.
followsInCanon
Indicates that one entity occurs later than and in continuity with another within an established narrative or canonical sequence.
-
E.
partOfCreativeCanonOf
Indicates that one creative work or element belongs to, and is recognized as a constituent part of, a larger established creative canon.
- 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_69f224820c048190b1435c4cc145acf1 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68f670b608190a0b6ab60d722b4e0 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f68b7b03488190b1db5fde4c7dd6e5 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 7:39 p.m.