Triple
T15254038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bertram Ramsay |
E364595
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Helen Menzies |
E364595
|
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: Helen Menzies | Statement: [Bertram Ramsay, spouse, Helen Menzies]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Helen Menzies Context triple: [Bertram Ramsay, spouse, Helen Menzies]
-
A.
Helen Menzies
chosen
Helen Menzies was the wife of British Admiral Sir Bertram Ramsay, a key naval commander during World War II.
-
B.
Helen Taggart
Helen Taggart was the wife of American architect Lloyd Wright, son of the famed architect Frank Lloyd Wright.
-
C.
Florence McKechnie
Florence McKechnie, better known by her stage name Florence Eldridge, was an American stage and film actress active in the early to mid-20th century.
-
D.
June Melville
June Melville was the first wife of English actor John Le Mesurier, known for her connection to his early personal life before his later fame in British television comedy.
-
E.
Helen McOuat
Helen McOuat was the wife of Scottish-born Canadian industrialist Henry Burden, known for her connection to his prominent 19th-century iron manufacturing enterprise in Troy, New York.
- 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_69d85a0dde7481908fc64d1e82d5d20d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e007f8cb308190933c4478aa096e24 |
completed | April 15, 2026, 9:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00b272ea6c8190b22fd78081446701 |
completed | May 10, 2026, 4:29 p.m. |
Created at: April 10, 2026, 3:13 a.m.