Triple
T27519729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Count of Ravensberg |
E694672
|
entity |
| Predicate | heldInPersonalUnionWith |
P13386
|
FINISHED |
| Object | Duchy of Jülich |
—
|
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: Duchy of Jülich | Statement: [Count of Ravensberg, heldInPersonalUnionWith, Duchy of Jülich]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldInPersonalUnionWith Context triple: [Count of Ravensberg, heldInPersonalUnionWith, Duchy of Jülich]
-
A.
countryOfReignAsConsort
Indicates the country over which a person held the status of consort during a reign.
-
B.
unionOfCrownsMonarch
Indicates that a monarch rules over multiple crowns or realms united under a single sovereign authority.
-
C.
spouseIsMonarchOf
Indicates that a person's spouse holds the position of monarch (ruler) of a specified country or territory.
-
D.
monarchConsortOf
Indicates that one person is the spouse of a reigning monarch, holding the role of consort to that monarch.
-
E.
dynasticUnion
chosen
Indicates a political relationship in which two or more distinct states are ruled by the same dynasty or monarch while formally remaining separate entities.
- 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_69ef538550208190aa9de8e2cb260d93 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6359e3d3c81909814e2f0a7fb0ea9 |
completed | May 2, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f631871c888190bf29466fe4254e51 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 1:20 p.m.