Triple
T872073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Birmingham pub bombings |
E18834
|
entity |
| Predicate | hasVictimMemorial |
P501
|
FINISHED |
| Object | memorial to the 21 victims in Birmingham |
—
|
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: memorial to the 21 victims in Birmingham | Statement: [Birmingham pub bombings, hasVictimMemorial, memorial to the 21 victims in Birmingham]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVictimMemorial Context triple: [Birmingham pub bombings, hasVictimMemorial, memorial to the 21 victims in Birmingham]
-
A.
hasMemorial
chosen
Indicates that a memorial exists in honor of, or dedicated to, a particular entity.
-
B.
hasAdjacentMemorial
Indicates that one memorial is located directly next to or in close proximity to another memorial.
-
C.
memorializesInjured
Indicates that one entity serves as a memorial or tribute to another entity that has been injured.
-
D.
commemoratedBy
Indicates that something is honored, remembered, or celebrated through a particular action, event, object, or representation.
-
E.
memorialType
Indicates the specific kind or category of memorial associated with an entity (e.g., plaque, statue, monument).
- 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_69a4938db1f081909bcd1ad2713b6096 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac96850881908a2d776685126137 |
completed | March 1, 2026, 9:16 p.m. |
| PD | Predicate disambiguation | batch_69a4aa8b9b5c81909ac71904f8b8b5cd |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.