Triple
T6715630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ballymun |
E153259
|
entity |
| Predicate | regenerationIncludes |
P71909
|
FINISHED |
| Object | demolition of tower blocks |
—
|
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: demolition of tower blocks | Statement: [Ballymun, regenerationIncludes, demolition of tower blocks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regenerationIncludes Context triple: [Ballymun, regenerationIncludes, demolition of tower blocks]
-
A.
regenerationOf
Indicates that one entity is the renewed, restored, or regrown version of another entity, typically after damage, loss, or degradation.
-
B.
regenerationAssociatedWith
chosen
Indicates an association between a regeneration process and a related factor, condition, or entity involved in or linked to that regenerative activity.
-
C.
regenerationContinuedIn
Indicates that an ongoing process of regeneration persists or is maintained within a specified context, location, or time period.
-
D.
featuresRegeneration
Indicates that an entity possesses the ability to regenerate or regrow lost or damaged parts.
-
E.
regenerationAbility
Indicates the capability of an entity to restore or regrow lost or damaged parts of itself.
- 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_69c68809b4608190a2509ddb5ab87f05 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d1246b748190aed94e8ab8625f7e |
completed | March 27, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69c6d08c5d348190a29dee668c398e70 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:07 p.m.