Triple
T19279896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torcuato Fernández-Miranda |
E482158
|
entity |
| Predicate | helpedDismantle |
P23233
|
FINISHED |
| Object | Francoist political structures |
—
|
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: Francoist political structures | Statement: [Torcuato Fernández-Miranda, helpedDismantle, Francoist political structures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helpedDismantle Context triple: [Torcuato Fernández-Miranda, helpedDismantle, Francoist political structures]
-
A.
dismantledBy
chosen
Indicates that something has been taken apart, disassembled, or broken down by a particular agent or entity.
-
B.
dismantledIn
Indicates that an entity was taken apart, disassembled, or broken down within a specified context, such as a particular time, place, or event.
-
C.
aimedToBeDismantledBy
Indicates that one entity was the intended target of dismantling or disassembly by another entity.
-
D.
demolished
Indicates that one entity completely destroyed or razed another entity, typically a structure or object, so that it no longer exists in its previous form.
-
E.
helpedImpose
Indicates that one entity assisted or contributed to another entity’s act of enforcing, establishing, or placing a rule, condition, or burden on something or someone.
- 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_69d8e8cf61b0819096fe3e4107827c4e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fbbf817c819098745ed365cda4a9 |
completed | April 20, 2026, 10:11 a.m. |
| PD | Predicate disambiguation | batch_69e4dd07a7208190afcd51ba1dc87c33 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:30 p.m.