Triple
T4734060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bayeux |
E105080
|
entity |
| Predicate | regionCapitalUntil |
P3417
|
FINISHED |
| Object | Caen became capital of Normandy |
—
|
LITERAL 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: Caen became capital of Normandy | Statement: [Bayeux, regionCapitalUntil, Caen became capital of Normandy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionCapitalUntil Context triple: [Bayeux, regionCapitalUntil, Caen became capital of Normandy]
-
A.
formerCapitalOf
chosen
Indicates that a place once served as the capital of another entity (such as a country or region) but no longer holds that status.
-
B.
capitalOfRuledEntity
Indicates that a city or settlement serves as the capital of a political entity that rules or governs another entity.
-
C.
servedAsNationalCapitalUntil
Indicates that a place functioned as the national capital of a country or state up to a specified end date, after which it no longer held that status.
-
D.
capitalOftenLocatedIn
Indicates that the capital city of a region or country is frequently, though not always, situated within a particular location or type of area.
-
E.
regionCapital
Indicates that one entity is the capital city or administrative center of a specified region.
- F. None of above.
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_69bd43ee52048190b81a4f066534ffb3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6467a1fc819089485b4d76e0edc4 |
completed | March 20, 2026, 3:14 p.m. |
| PD | Predicate disambiguation | batch_69bd6221c3b881908604f35f8de6f16b |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:19 p.m.