Triple
T19012291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herleve |
E465256
|
entity |
| Predicate | maritalStatusWithRobert I, Duke of Normandy |
P134113
|
FINISHED |
| Object | not married |
—
|
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: not married | Statement: [Herleve, maritalStatusWithRobert I, Duke of Normandy, not married]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maritalStatusWithRobert I, Duke of Normandy Context triple: [Herleve, maritalStatusWithRobert I, Duke of Normandy, not married]
-
A.
marriageToEdwardTheConfessor
Indicates a marital relationship in which the subject is married to Edward the Confessor.
-
B.
reignAsDukeOfNormandyTo
Indicates that one entity holds and exercises the title and authority of Duke of Normandy over another entity (typically a territory or domain).
-
C.
marriageToHenryVIIIStatus
Indicates the status or condition of an entity’s marriage relationship to Henry VIII (e.g., current, former, annulled, pending, etc.).
-
D.
marriageDateToEmpressMatilda
Indicates the date on which an individual married Empress Matilda.
-
E.
reignEndAsDukeOfNormandy
Indicates the time or event at which an individual's rule or authority as Duke of Normandy comes to an end.
- F. None of above. chosen
Provenance (4 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_69d8dd025c188190a1d81f5b4ec7e2c6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a9bac8819093f9af57000667b0 |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2fd80c081908237317a3a883e1c |
completed | April 19, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69e4ad8e075c8190ad561edc5e520057 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, 12:02 p.m.