Triple
T29339739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Star Wars Skywalker saga films |
E744004
|
entity |
| Predicate | originalTrilogyStart |
P20449
|
FINISHED |
| Object | Star Wars: Episode IV – A New Hope |
—
|
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: Star Wars: Episode IV – A New Hope | Statement: [Star Wars Skywalker saga films, originalTrilogyStart, Star Wars: Episode IV – A New Hope]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalTrilogyStart Context triple: [Star Wars Skywalker saga films, originalTrilogyStart, Star Wars: Episode IV – A New Hope]
-
A.
chronologicalOrderInOriginalTrilogy
Indicates the sequence in which events or items appear in time within the original trilogy.
-
B.
eraStartRelativeToSkywalkerSaga
Indicates how the beginning of a given era is positioned in time relative to the events of the Skywalker Saga.
-
C.
trilogyDepicts
Indicates that a trilogy portrays, represents, or narratively focuses on a particular subject, event, or set of entities.
-
D.
partOfTrilogy
Indicates that one work belongs to a set of three related works that together form a trilogy.
-
E.
filmSeriesStart
chosen
Indicates that a particular film marks the beginning or first installment of a film series.
- 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_69f09126cfcc8190899b16fbf3c2bf7b |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69ff9361943c81909544203cbc998a69 |
completed | May 9, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69ff913138a08190b59bdc9d8d199eb3 |
completed | May 9, 2026, 7:55 p.m. |
Created at: April 28, 2026, 1:33 p.m.