Triple
T8415391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blade Runner |
E198718
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Daryl Hannah |
E78247
|
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: Daryl Hannah | Statement: [Blade Runner, starring, Daryl Hannah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daryl Hannah Context triple: [Blade Runner, starring, Daryl Hannah]
-
A.
Daryl Hannah
chosen
Daryl Hannah is an American actress best known for her roles in films such as "Splash," "Blade Runner," and "Kill Bill."
-
B.
Lauren Holly
Lauren Holly is an American-Canadian actress best known for her roles in films like "Dumb and Dumber" and the TV series "NCIS."
-
C.
Kristy McNichol
Kristy McNichol is an American actress best known for her Emmy-winning role on the TV drama "Family" and her work in films like "Little Darlings" and "Only When I Laugh."
-
D.
Lea Thompson
Lea Thompson is an American actress best known for her role as Lorraine Baines McFly in the Back to the Future film trilogy.
-
E.
Tanya Roberts
Tanya Roberts was an American actress and model best known for her roles in the James Bond film "A View to a Kill," the TV series "Charlie's Angels," and "That '70s Show."
- 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_69ca831201b481909e137936ef99ff11 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb83e443a08190983d9a0a61e0f781 |
completed | March 31, 2026, 8:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce6ce5bfe481909e05c6a34e10ae16 |
completed | April 2, 2026, 1:19 p.m. |
Created at: March 30, 2026, 6:06 p.m.