Triple
T16530124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coventry Blitz |
E401540
|
entity |
| Predicate | defence |
P108546
|
FINISHED |
| Object | anti-aircraft guns around Coventry |
—
|
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: anti-aircraft guns around Coventry | Statement: [Coventry Blitz, defence, anti-aircraft guns around Coventry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defence Context triple: [Coventry Blitz, defence, anti-aircraft guns around Coventry]
-
A.
defense
Indicates an action or relationship in which an entity protects, guards, or resists against a threat, attack, or criticism from another entity.
-
B.
defends
Indicates that one entity protects or supports another entity against attack, criticism, or harm.
-
C.
defenceBody
Indicates a relationship where an entity serves as the official body or organization responsible for defense or military affairs of another entity (such as a country or jurisdiction).
-
D.
defender
Indicates a relationship where one entity protects, guards, or supports another entity against threats, attacks, or criticism.
-
E.
defenseIncludes
chosen
Indicates that a defense strategy, plan, or system contains or incorporates a particular component, measure, or element as part of it.
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32ed625208190a68b879266b05b3f |
completed | April 18, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69e296995d388190b88ebe189dce890d |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:14 a.m.