Triple
T29321987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duel on Mustafar |
E743538
|
entity |
| Predicate | marksTurningPointFor |
P676
|
FINISHED |
| Object | Anakin Skywalker |
—
|
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: Anakin Skywalker | Statement: [Duel on Mustafar, marksTurningPointFor, Anakin Skywalker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marksTurningPointFor Context triple: [Duel on Mustafar, marksTurningPointFor, Anakin Skywalker]
-
A.
turningPointIn
chosen
Indicates that an event or situation serves as a decisive change or pivotal moment within a larger process, narrative, or development.
-
B.
marksOn
Indicates that one entity bears visible signs, traces, or imprints that have been made or left by another entity.
-
C.
marksApproachTo
Indicates that one entity signifies or designates the way or method by which another entity is approached.
-
D.
marksMeetingPointOf
Indicates that something designates or identifies the specific location where two or more entities meet or converge.
-
E.
marksLabelTransitionTo
Indicates that something designates or signals the point at which one label changes or transitions to another label.
- 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_69f09125f784819080f4e9fce9fe624f |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f668933d288190a5c9437db2b9de01 |
completed | May 2, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69f660f2e3708190ab658652bcfc04d0 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 1:23 p.m.