Triple
T12627754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angus Ogilvy |
E301559
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Marina Ogilvy |
E301560
|
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: Marina Ogilvy | Statement: [Angus Ogilvy, child, Marina Ogilvy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marina Ogilvy Context triple: [Angus Ogilvy, child, Marina Ogilvy]
-
A.
Marina Ogilvy
chosen
Marina Ogilvy is a British aristocrat known as the daughter of Princess Alexandra of Kent and a member of the extended British royal family.
-
B.
Julia Ogilvy
Julia Ogilvy is a Scottish businesswoman and charity patron who married into the extended British royal family as the wife of James Ogilvy, a grandson of Queen Elizabeth II.
-
C.
Emily Lloyd
Emily Lloyd is a British actress best known for her acclaimed breakthrough role in the 1987 film "Wish You Were Here."
-
D.
Clarissa Luard
Clarissa Luard was a British literary editor and arts administrator known for her work supporting contemporary writers and for her marriage to novelist Salman Rushdie.
-
E.
Elizabeth Rogers
Elizabeth Rogers was an American actress known for her film and television roles in the 1960s and 1970s.
- 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9610b91dc8190a9abefb88447b0ae |
completed | April 10, 2026, 8:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6719676d48190bcc9d7ccbde2605e |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:15 p.m.