Triple
T13081836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Latymer Upper School |
E310225
|
entity |
| Predicate | hasAlumni |
P51
|
FINISHED |
| Object |
Cressida Dick
Cressida Dick is a British senior police officer who served as the first female Commissioner of London's Metropolitan Police Service.
|
E1019654
|
NE FINISHED |
How this triple was built (4 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: Cressida Dick | Statement: [Latymer Upper School, hasAlumni, Cressida Dick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cressida Dick Context triple: [Latymer Upper School, hasAlumni, Cressida Dick]
-
A.
Stella Rimington
Stella Rimington is a British intelligence officer and author best known for serving as the first female Director General of MI5.
-
B.
Elizabeth Jeffreys
Elizabeth Jeffreys was an 18th-century British noblewoman best known as the wife of Charles Pratt, 1st Earl Camden, a prominent jurist and politician.
-
C.
Louise Shore
Louise Shore is a television producer best known for her executive production work on the miniseries "A Teacher."
-
D.
Jennifer Mordaunt
Jennifer Mordaunt is a relative of British Conservative politician Penny Mordaunt.
-
E.
Lynda La Plante
Lynda La Plante is a British novelist, screenwriter, and former actress best known for her gritty crime dramas and influential work in television police procedurals.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cressida Dick Triple: [Latymer Upper School, hasAlumni, Cressida Dick]
Generated description
Cressida Dick is a British senior police officer who served as the first female Commissioner of London's Metropolitan Police Service.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Cressida Dick Target entity description: Cressida Dick is a British senior police officer who served as the first female Commissioner of London's Metropolitan Police Service.
-
A.
Stella Rimington
Stella Rimington is a British intelligence officer and author best known for serving as the first female Director General of MI5.
-
B.
Elizabeth Jeffreys
Elizabeth Jeffreys was an 18th-century British noblewoman best known as the wife of Charles Pratt, 1st Earl Camden, a prominent jurist and politician.
-
C.
Louise Shore
Louise Shore is a television producer best known for her executive production work on the miniseries "A Teacher."
-
D.
Jennifer Mordaunt
Jennifer Mordaunt is a relative of British Conservative politician Penny Mordaunt.
-
E.
Lynda La Plante
Lynda La Plante is a British novelist, screenwriter, and former actress best known for her gritty crime dramas and influential work in television police procedurals.
- F. None of above. chosen
Provenance (5 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_69d806a733548190989cfd4ce981ca33 |
completed | April 9, 2026, 8:05 p.m. |
| NER | Named-entity recognition | batch_69d9811add9881908a92186dab5b6d48 |
completed | April 10, 2026, 11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d60e7b48819087e4583a5736c1df |
completed | May 3, 2026, 4:58 a.m. |
| NEDg | Description generation | batch_69f6d76cc33c8190ac8113094bcf868b |
completed | May 3, 2026, 5:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6d8013e9481908f5edcce7247212d |
completed | May 3, 2026, 5:07 a.m. |
Created at: April 9, 2026, 9:01 p.m.