Triple
T26327967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Howel the Good |
E662305
|
entity |
| Predicate | soughtPolicy |
P160251
|
FINISHED |
| Object | political unification of Wales |
—
|
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: political unification of Wales | Statement: [Howel the Good, soughtPolicy, political unification of Wales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: soughtPolicy Context triple: [Howel the Good, soughtPolicy, political unification of Wales]
-
A.
soughtPolicy
chosen
Indicates that an entity actively pursued, requested, or attempted to obtain a particular policy.
-
B.
establishedPolicy
Indicates that a policy has been formally created, adopted, and put into effect as a guiding rule or standard.
-
C.
soughtTo
Indicates that one entity attempted or intended to obtain, achieve, or bring about another entity or outcome.
-
D.
publicPolicy
Indicates that an entity is a government or institutional rule, principle, or course of action intended to address public issues or guide societal outcomes.
-
E.
targetedPolicy
Indicates that a policy is specifically directed at, or designed to affect, a particular subset of entities rather than applying broadly.
- 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_69ee812f32748190871d970c4e2a8ddf |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60f67045c8190883d6d73a2b84320 |
completed | May 2, 2026, 2:51 p.m. |
| PD | Predicate disambiguation | batch_69f602d2ec748190ae95154f34c7878f |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 26, 2026, 10:32 p.m.