Triple
T17048064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1998 Birmingham abortion clinic bombing |
E413620
|
entity |
| Predicate | FBIClassification |
P125649
|
FINISHED |
| Object | act of domestic terrorism |
—
|
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: act of domestic terrorism | Statement: [1998 Birmingham abortion clinic bombing, FBIClassification, act of domestic terrorism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: FBIClassification Context triple: [1998 Birmingham abortion clinic bombing, FBIClassification, act of domestic terrorism]
-
A.
hasUCIClassification
Indicates that an entity is assigned a specific classification according to the UCI (Union Cycliste Internationale) categorization system.
-
B.
UICClassification
Indicates the standardized classification or coding assigned to an entity according to the UIC (International Union of Railways) system.
-
C.
areClassifiedBy
Indicates that entities are assigned to one or more categories, types, or classes according to a specified classification scheme.
-
D.
outputClassification
Indicates how a given output is categorized or labeled according to a specified classification scheme.
-
E.
usesClassificationCriteria
Indicates that one entity applies specific classification criteria to categorize, organize, or evaluate another entity.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3da9f799c8190a683ae38cd990643 |
completed | April 18, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69e35d60a588819084f53ef9f8b2e7c0 |
completed | April 18, 2026, 10:30 a.m. |
| PDg | Predicate description generation | batch_69e3753f93c88190808fec5692f66699 |
completed | April 18, 2026, 12:12 p.m. |
Created at: April 10, 2026, 5:34 a.m.