Triple
T9207673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alfred Curzon, 4th Baron Scarsdale |
E221026
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Curzon |
E614372
|
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: Curzon | Statement: [Alfred Curzon, 4th Baron Scarsdale, familyName, Curzon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Curzon Context triple: [Alfred Curzon, 4th Baron Scarsdale, familyName, Curzon]
-
A.
Curzon
chosen
Curzon is a notable British surname historically associated with aristocratic families and political figures in the United Kingdom.
-
B.
Talbot
Talbot is a surname of English and Norman origin, historically associated with several notable families and individuals.
-
C.
Williamswood
Williamswood is a small suburban community in the Halifax Regional Municipality of Nova Scotia, Canada.
-
D.
Cadogan
Cadogan is a British surname historically associated with an Anglo-Irish aristocratic family and several notable figures in politics, the military, and public life.
-
E.
Winstone
Winstone is an English surname most notably borne by actor Ray Winstone, known for his tough-guy roles in film and television.
- 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_69ca83e9d0e081908bdb71097201a06c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd9b217008190a0ab4971dd4a8899 |
completed | April 1, 2026, 8:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d065e49fcc81909ddb838a8ad28c57 |
completed | April 4, 2026, 1:14 a.m. |
Created at: March 30, 2026, 7:26 p.m.