Triple
T31529869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mayor of the Palace of Austrasia |
E804446
|
entity |
| Predicate | officeHolderFamily |
P114381
|
FINISHED |
| Object | Arnulfings |
—
|
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: Arnulfings | Statement: [Mayor of the Palace of Austrasia, officeHolderFamily, Arnulfings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeHolderFamily Context triple: [Mayor of the Palace of Austrasia, officeHolderFamily, Arnulfings]
-
A.
associatedPoliticalFamily
chosen
Indicates a relationship where an entity is linked or connected to a particular political family, dynasty, or lineage.
-
B.
familyOf
Indicates a familial relationship exists between the entities, such as by blood, marriage, or adoption.
-
C.
FirstFamily
Indicates a familial relationship where one entity is recognized as the primary or original family associated with another entity (such as a person, role, or position).
-
D.
officeHolderParent
Indicates that one entity is the parent of another entity who holds or has held a particular office or official position.
-
E.
ownerFamily
Indicates that a family has ownership or proprietary rights over a particular entity or resource.
- 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_69f348d03ef88190a2b73d7b94b9e02d |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fec5c503808190bde0b1829ea43071 |
completed | May 9, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69fec535dd6c8190a6ab85201f5a04a9 |
completed | May 9, 2026, 5:25 a.m. |
Created at: April 30, 2026, 10 p.m.