Triple
T9163614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Curzon, 1st Earl Curzon of Kedleston |
E219889
|
entity |
| Predicate | honorificSuffix |
P341
|
FINISHED |
| Object | KG |
E5304
|
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: KG | Statement: [George Curzon, 1st Earl Curzon of Kedleston, honorificSuffix, KG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KG Context triple: [George Curzon, 1st Earl Curzon of Kedleston, honorificSuffix, KG]
-
A.
KG
chosen
KG is the post-nominal abbreviation used by Knights of the Order of the Garter, the highest order of chivalry in the United Kingdom.
-
B.
KG
KG is the widely used nickname of Kevin Garnett, a Hall of Fame NBA forward known for his intensity, defensive prowess, and versatility.
-
C.
KGX
KGX is the National Rail station code for London King's Cross, a major central London railway terminus and transport hub.
-
D.
KGH
KGH is the National Rail station code for Kinghorn railway station in Fife, Scotland.
-
E.
KER
KER is the stock ticker symbol for Kering, the French multinational luxury goods group that owns brands such as Gucci, Saint Laurent, and Bottega Veneta.
- 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_69ca83e3633c81908688a9fa2306ba99 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccaa2d6628819084ac4734650fe912 |
completed | April 1, 2026, 5:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0547df750819095853f21cf740c63 |
completed | April 3, 2026, 11:59 p.m. |
Created at: March 30, 2026, 7:21 p.m.