Triple
T3580131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Star Wars: The Rise of Skywalker |
E75778
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Carrie Fisher |
E146866
|
NE FINISHED |
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: Carrie Fisher | Statement: [Star Wars: The Rise of Skywalker, castMember, Carrie Fisher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carrie Fisher Context triple: [Star Wars: The Rise of Skywalker, castMember, Carrie Fisher]
-
A.
Carrie Fisher
chosen
Carrie Fisher was an American actress and writer best known for her iconic role as Princess Leia in the Star Wars film series.
-
B.
Kate Mara
Kate Mara is an American actress known for her roles in films like "The Martian" and "Brokeback Mountain" and TV series such as "House of Cards."
-
C.
Sully Erna
Sully Erna is an American musician best known as the lead vocalist and primary songwriter of the hard rock band Godsmack.
-
D.
Talia Shire
Talia Shire is an American actress best known for her roles as Adrian in the Rocky film series and Connie Corleone in The Godfather trilogy.
-
E.
Daryl Hannah
Daryl Hannah is an American actress best known for her roles in films such as "Splash," "Blade Runner," and "Kill Bill."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0ffecdc8190bf01c8ba90e3733e |
completed | March 8, 2026, 6:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b402f36b2481909d4716e72a696e0d |
completed | March 13, 2026, 12:28 p.m. |
Created at: March 8, 2026, 3:21 p.m.