Triple
T23063679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arnulf I, Count of Flanders |
E574974
|
entity |
| Predicate | reignOrInOffice |
P87123
|
FINISHED |
| Object | 918–965 |
—
|
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: 918–965 | Statement: [Arnulf I, Count of Flanders, reignOrInOffice, 918–965]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reignOrInOffice Context triple: [Arnulf I, Count of Flanders, reignOrInOffice, 918–965]
-
A.
activeInReignOf
Indicates that an entity was active or operational during the time period corresponding to a specific ruler’s reign.
-
B.
reignedFrom
chosen
Indicates the time period during which an entity held ruling authority or sovereignty over a domain.
-
C.
headOfStateDuringReign
Indicates that one entity served as the head of state for another entity during a specified reign or ruling period.
-
D.
reignedUnder
Indicates that one entity exercised ruling authority or governance while being subordinate to, or under the higher sovereignty of, another entity.
-
E.
regentPreviouslyHeldOffice
Indicates that the regent held a particular office or position before assuming their regency.
- 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f189a1f49c81909db7e0473ec2bb1b |
completed | April 29, 2026, 4:31 a.m. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:55 p.m.