Triple
T38659257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchess of Bedford |
E939983
|
entity |
| Predicate | creationLinkedTo |
P201689
|
FINISHED |
| Object | Dukedom of Bedford |
—
|
NE NERFINISHED |
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: Dukedom of Bedford | Statement: [Duchess of Bedford, creationLinkedTo, Dukedom of Bedford]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creationLinkedTo Context triple: [Duchess of Bedford, creationLinkedTo, Dukedom of Bedford]
-
A.
creationAnnounced
Indicates that an entity has publicly announced the initiation or establishment of another entity or creation.
-
B.
createsRelationshipWith
Indicates that one entity establishes or initiates a new relationship or association with another entity.
-
C.
createdAsOutcomeOf
Indicates that one entity was brought into existence specifically as a result or consequence of another event, process, or action.
-
D.
relatedWorkCreator
Indicates that the creator of one work is related (e.g., by authorship, contribution, or collaboration) to the creation of another work.
-
E.
seriesCreatorConnection
Indicates a relationship where one entity is the creator or originator of a series associated with another entity.
- 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_69f76ede49648190a48bfe47032a05a3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00144238708190acbec3f791cc873e |
completed | May 10, 2026, 5:14 a.m. |
| PD | Predicate disambiguation | batch_6a00120244a4819090ef39070aba9d99 |
completed | May 10, 2026, 5:05 a.m. |
| PDg | Predicate description generation | batch_6a001440a26c81908ba50779bb6e1679 |
completed | May 10, 2026, 5:14 a.m. |
Created at: May 3, 2026, 4:33 p.m.