Triple
T12794762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Will Turner |
E305859
|
entity |
| Predicate | loyalTo |
P1201
|
FINISHED |
| Object | Elizabeth Swann |
E265093
|
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: Elizabeth Swann | Statement: [Will Turner, loyalTo, Elizabeth Swann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Swann Context triple: [Will Turner, loyalTo, Elizabeth Swann]
-
A.
Elizabeth Swann
chosen
Elizabeth Swann is a courageous and resourceful governor’s daughter-turned-pirate leader in the Pirates of the Caribbean film series.
-
B.
Sally Sparrow
Sally Sparrow is a resourceful young woman who becomes entangled with the Weeping Angels and the Doctor in the acclaimed Doctor Who episode "Blink."
-
C.
Madeleine Swann
Madeleine Swann is a French psychologist and the primary Bond girl and love interest of James Bond in the Daniel Craig-era films "Spectre" and "No Time to Die."
-
D.
Kelly Crabb
Kelly Crabb is a film editor known for her work on the documentary thriller "The Cove."
-
E.
Lisa Zane
Lisa Zane is an American actress and singer known for her roles in film and television, including appearances in projects like "Freddy's Dead: The Final Nightmare" and the series "Profit."
- 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_69d7bdf366888190a8cccb982606889c |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e6ca0288190aba01735b71a01da |
completed | April 10, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68ebeab2081908a6e38351613e3ed |
completed | May 2, 2026, 11:54 p.m. |
Created at: April 9, 2026, 5:30 p.m.