Triple
T10941983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haggerston |
E258494
|
entity |
| Predicate | hasRegenerationType |
P96762
|
FINISHED |
| Object | waterside redevelopment along Regent's Canal |
—
|
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: waterside redevelopment along Regent's Canal | Statement: [Haggerston, hasRegenerationType, waterside redevelopment along Regent's Canal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRegenerationType Context triple: [Haggerston, hasRegenerationType, waterside redevelopment along Regent's Canal]
-
A.
hasRegenerationCycleWith
Indicates that two entities are linked by a recurring regeneration or renewal process that they undergo together or in relation to each other.
-
B.
hasMultipleRegenerations
Indicates that an entity has undergone more than one process of regeneration or renewal.
-
C.
regenerationAbility
Indicates the capability of an entity to restore or regrow lost or damaged parts of itself.
-
D.
regenerationOf
Indicates that one entity is the renewed, restored, or regrown version of another entity, typically after damage, loss, or degradation.
-
E.
hasReproductionType
Indicates the mode or method by which an entity reproduces or generates offspring.
- F. None of above. chosen
Provenance (4 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_69d6aa8769b4819082bfe5e61b9017f0 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770c33a7c8190b3347944f68ee431 |
completed | April 9, 2026, 9:26 a.m. |
| PD | Predicate disambiguation | batch_69d72e816a98819096d6c10dfb88a66a |
completed | April 9, 2026, 4:43 a.m. |
| PDg | Predicate description generation | batch_69d7322370648190ba14cdd6fb4cdcb0 |
completed | April 9, 2026, 4:59 a.m. |
Created at: April 8, 2026, 9:23 p.m.