Triple
T15103238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German armoured cruiser Blücher |
E360720
|
entity |
| Predicate | enteredServiceBefore |
P117335
|
FINISHED |
| Object | German battlecruisers |
—
|
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: German battlecruisers | Statement: [German armoured cruiser Blücher, enteredServiceBefore, German battlecruisers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enteredServiceBefore Context triple: [German armoured cruiser Blücher, enteredServiceBefore, German battlecruisers]
-
A.
enteredService
Indicates that an entity began active use or operation at a specific time or in a specific context.
-
B.
enteredServiceWithUnit
Indicates that an entity began its period of service or active duty while assigned to a specified unit.
-
C.
enteredServiceWithOperator
Indicates that an entity began operational service under the responsibility or control of a specified operator.
-
D.
enteredANGService
Indicates that an entity has begun or been inducted into service within the ANG (Air National Guard).
-
E.
enteredServiceAsReplacementFor
Indicates that one entity began its period of service specifically to take over the role or function previously performed by 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_69d85a0491ec8190830960be8fafb994 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00551521c8190b48d1a074bb4bdfc |
completed | April 15, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69deb96c1d9c81909351558ed97bc5b7 |
completed | April 14, 2026, 10:02 p.m. |
| PDg | Predicate description generation | batch_69dec71e8dcc81908badc834b6ccf273 |
completed | April 14, 2026, 11 p.m. |
Created at: April 10, 2026, 3:05 a.m.