Triple
T21992021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annabel Banks |
E543112
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | John Banks |
—
|
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: John Banks | Statement: [Annabel Banks, sibling, John Banks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Banks Context triple: [Annabel Banks, sibling, John Banks]
-
A.
John Banks
John Banks is a musician best known as a member of the 1960s British beat group The Merseybeats.
-
B.
John Banks
John Banks is a fictional child character in the Mary Poppins stories and their film adaptations.
-
C.
David Banks
David Banks is a music producer known for his work on the album "…Is It Something I Said?".
-
D.
Christopher Banks
Christopher Banks is the introspective English detective and narrator of Kazuo Ishiguro’s novel "When We Were Orphans," whose search for his vanished parents in Shanghai drives the story’s exploration of memory and identity.
-
E.
Tom Bancroft
Tom Bancroft is an American animator, illustrator, and character designer best known for his work on Disney films such as "Mulan" and "The Lion King."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69e0c48136b081908831fa907cc02e18 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1270e951081908deda039b47ca84b |
completed | April 28, 2026, 9:30 p.m. |
Created at: April 16, 2026, 8:05 p.m.