Triple
T29020376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duff Dry |
E737435
|
entity |
| Predicate | brandOwnerInFiction |
P14482
|
FINISHED |
| Object | Duff Brewery |
—
|
NE NERFINISHED |
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: Duff Brewery | Statement: [Duff Dry, brandOwnerInFiction, Duff Brewery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brandOwnerInFiction Context triple: [Duff Dry, brandOwnerInFiction, Duff Brewery]
-
A.
formerOwnerInFiction
Indicates that one entity is depicted in a fictional context as having previously owned another entity.
-
B.
ownedByFictionalCharacter
Indicates that something is possessed or owned by a fictional (not real-world) character.
-
C.
fictionalUniverseOwner
Indicates that one entity is the creator, rights holder, or controlling owner of a particular fictional universe or setting.
-
D.
brandCharacter
Indicates that one entity serves as a brand character or mascot representing another entity (typically a brand or product).
-
E.
hasFictionalProprietor
chosen
Indicates that something is owned, managed, or run by a fictional character or entity within a narrative context.
- 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_69f077ee19f881909af48f9cab00a2e5 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 9:48 a.m.