Triple
T18378131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarzan's Greatest Adventure |
E446369
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Sara Shane |
—
|
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: Sara Shane | Statement: [Tarzan's Greatest Adventure, starring, Sara Shane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sara Shane Context triple: [Tarzan's Greatest Adventure, starring, Sara Shane]
-
A.
Sara Shane
chosen
Sara Shane was an American film and television actress best known for her roles in 1950s Hollywood dramas and adventure films.
-
B.
Samantha Shane
Samantha Shane is a U.S. Navy petty officer and physical therapist who becomes a key member of the human resistance against an alien invasion in the science-fiction film "Battleship."
-
C.
Sarah Shayne
Sarah Shayne is a character from the soap opera "Guiding Light," known primarily as the mother of Reva Shayne.
-
D.
Rachel Shane
Rachel Shane is a film and television producer known for her executive work on various high-profile projects, including the TV series "Genius."
-
E.
Sharni Vinson
Sharni Vinson is an Australian actress and dancer best known for her roles in films like "Step Up 3D" and the horror movie "You're Next."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f370b88190b1e5081c2c238e7f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e5179919c881908d55ea24f93c5827 |
completed | April 19, 2026, 5:57 p.m. |
Created at: April 10, 2026, 10:45 a.m.