Triple
T10948219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Panzergrenadier-Regiment 104 |
E258651
|
entity |
| Predicate | hasUnitTypeCharacteristic |
P274
|
FINISHED |
| Object | combined arms cooperation with tanks |
—
|
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: combined arms cooperation with tanks | Statement: [Panzergrenadier-Regiment 104, hasUnitTypeCharacteristic, combined arms cooperation with tanks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUnitTypeCharacteristic Context triple: [Panzergrenadier-Regiment 104, hasUnitTypeCharacteristic, combined arms cooperation with tanks]
-
A.
hasUnitOf
Indicates that a quantity, measurement, or value is expressed in terms of a specific unit.
-
B.
basedUnitType
Indicates that one unit is defined or derived in terms of another underlying (base) unit type.
-
C.
hasCharacteristic
chosen
Indicates that an entity possesses, exhibits, or is defined by a particular attribute, feature, or quality.
-
D.
hasBasicUnit
Indicates that one entity is composed of, defined by, or fundamentally characterized through another entity that serves as its basic or minimal unit.
-
E.
typeOfUnit
Indicates that one entity specifies the kind or category of measurement unit that the other entity belongs to.
- 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_69d6aa8769b4819082bfe5e61b9017f0 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770ebac3c8190849ddda3d9d37327 |
completed | April 9, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69d72e816a98819096d6c10dfb88a66a |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:23 p.m.