Triple
T29893221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Star Wars original trilogy |
E759207
|
entity |
| Predicate | hasCharacterPortrayedByDavidProwse |
P190491
|
FINISHED |
| Object | Darth Vader |
—
|
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: Darth Vader | Statement: [Star Wars original trilogy, hasCharacterPortrayedByDavidProwse, Darth Vader]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCharacterPortrayedByDavidProwse Context triple: [Star Wars original trilogy, hasCharacterPortrayedByDavidProwse, Darth Vader]
-
A.
characterPlayedByRichardHarris
Indicates that the subject is a character that was portrayed by the actor Richard Harris.
-
B.
HarrisonFordPlays
Indicates that Harrison Ford performs the role of a character in a specified film or work.
-
C.
voiceOfDarthVaderProvidedBy
Indicates that one entity is the person or source that provided the voice for the character Darth Vader.
-
D.
worksForCharacterPlayedBy
Indicates that one character is employed by, or works under, another character who is portrayed by a specific actor.
-
E.
hasStarshipClassDepicted
Indicates that an entity includes or shows a depiction of a particular starship class.
- 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_69f2245f1cf88190978c70d1a1d2cb73 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fcc7779d248190afdb348a95375443 |
completed | May 7, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69fcc58566a0819082d5ea36e03bf0c6 |
completed | May 7, 2026, 5:01 p.m. |
| PDg | Predicate description generation | batch_69fcc73264e08190b0b5917f32226fae |
completed | May 7, 2026, 5:09 p.m. |
Created at: April 29, 2026, 6:03 p.m.