Triple
T25797427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inglourious Basterds (commando unit) |
E649724
|
entity |
| Predicate | memberInFiction |
P104242
|
FINISHED |
| Object | Donny Donowitz |
—
|
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: Donny Donowitz | Statement: [Inglourious Basterds (commando unit), memberInFiction, Donny Donowitz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memberInFiction Context triple: [Inglourious Basterds (commando unit), memberInFiction, Donny Donowitz]
-
A.
worksInFictionalContext
Indicates that an entity performs work or fulfills a role within a fictional or imagined setting rather than in real-world circumstances.
-
B.
createsInFiction
Indicates that one entity is the creator or originator of another entity within a fictional or narrative context.
-
C.
hasFictionalMember
Indicates that a group, organization, or collection includes at least one member that is fictional rather than real.
-
D.
associatedWithFictionalGroup
chosen
Indicates that an entity has a connection or affiliation with a fictional group, organization, or collective.
-
E.
composedByFictionalCharacter
Indicates that a work or piece of content is (within the narrative) created or authored by a fictional character.
- 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_69e7ab34f8c8819099f6c4dabdabf129 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f67c9fe7b48190b79b4041357edb49 |
completed | May 2, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69f678cc272081909e5c70f1bc7407f0 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 22, 2026, 6:32 a.m.