Triple
T19510236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Midland Bank |
E488129
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object | Charles Geach |
—
|
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: Charles Geach | Statement: [Midland Bank, founder, Charles Geach]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles Geach Context triple: [Midland Bank, founder, Charles Geach]
-
A.
Charles Geach
chosen
Charles Geach was a 19th-century British banker and businessman best known for establishing Midland Bank, which grew into one of the United Kingdom’s major banking institutions.
-
B.
Geoffrey Carroll
Geoffrey Carroll is the sinister artist and bigamist at the center of the 1947 film noir thriller "The Two Mrs. Carrolls."
-
C.
Geoffrey Hinchliffe
Geoffrey Hinchliffe is an actor best known for his role in the British film "Made in Britain."
-
D.
Geoffrey Unsworth
Geoffrey Unsworth was a renowned British cinematographer celebrated for his visually rich work on numerous classic films of the 1960s and 1970s.
-
E.
Charles Matthews
Charles Matthews is a name shared by several notable individuals, including politicians, athletes, and public figures distinguished in their respective fields.
- 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6351547e481909a875bba40651094 |
completed | April 20, 2026, 2:15 p.m. |
Created at: April 10, 2026, 1:40 p.m.