Triple
T20319011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dukes of Norfolk |
E492157
|
entity |
| Predicate | originalCreationYear |
P9428
|
FINISHED |
| Object | 1397 |
—
|
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: 1397 | Statement: [Dukes of Norfolk, originalCreationYear, 1397]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalCreationYear Context triple: [Dukes of Norfolk, originalCreationYear, 1397]
-
A.
firstCreationYear
Indicates the year in which something was first created or originally produced.
-
B.
originYear
chosen
Indicates the year in which something first originated, was created, or began.
-
C.
estimatedYearOfCreation
Indicates the year in which something is believed or approximated to have been created, rather than a precisely known creation year.
-
D.
workOriginYear
Indicates the year in which a work (such as a creative, scholarly, or artistic piece) was originally created or first produced.
-
E.
firstVersionYear
Indicates the calendar year in which the first version or initial release of something was created, published, or made available.
- 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_69e0b4a0134081909113563e1c3ba68a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67789d8108190ae2e134f4b0b0be5 |
completed | April 20, 2026, 6:59 p.m. |
| PD | Predicate disambiguation | batch_69e55b23a0788190bf1853ef5b81823f |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 16, 2026, 11:20 a.m.