Triple
T8120909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montacute |
E189604
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Montagu |
E44847
|
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: Montagu | Statement: [Montacute, hasVariant, Montagu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Montagu Context triple: [Montacute, hasVariant, Montagu]
-
A.
Montagu
chosen
Montagu is a British noble family name most famously associated with John Montagu, 4th Earl of Sandwich, after whom the sandwich is named.
-
B.
Montagu
Montagu is a historic spa and farming town in South Africa’s Western Cape, known for its hot mineral springs, mountain scenery, and fruit and wine production.
-
C.
Moorfield
Moorfield is a given name most notably borne by Moorfield Storey, an American lawyer and civil rights leader who served as the first president of the NAACP.
-
D.
Egremont
Egremont is a small rural town in southwestern Massachusetts known for its scenic Berkshire landscapes and historic New England character.
-
E.
Egremont
Egremont is a district within the town of Wallasey on the Wirral Peninsula in Merseyside, England.
- 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_69ca82bb74848190afb1f18640632c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb435b72888190ad6330b375ed1eff |
completed | March 31, 2026, 3:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd678a4b548190b9d1a584d9139888 |
completed | April 1, 2026, 6:44 p.m. |
Created at: March 30, 2026, 5:33 p.m.