Triple
T4079687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | World War II CIB |
E87446
|
entity |
| Predicate | appliesToUnitType |
P28425
|
FINISHED |
| Object | infantry regiment |
—
|
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: infantry regiment | Statement: [World War II CIB, appliesToUnitType, infantry regiment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToUnitType Context triple: [World War II CIB, appliesToUnitType, infantry regiment]
-
A.
appliesToProductType
Indicates that something (such as a rule, offer, or condition) is relevant or applicable specifically to a certain type or category of product.
-
B.
appliesTo
Indicates that something is relevant, valid, or has effect in relation to a particular entity, case, or context.
-
C.
associatedUnitType
chosen
Indicates that one entity is linked to or characterized by a particular type or category of unit.
-
D.
appliedToVehicleType
Indicates that something (such as a rule, restriction, or condition) is specifically applicable to a particular type or category of vehicle.
-
E.
appliesToPropertyType
Indicates that something (such as a rule, constraint, or operation) is relevant to or valid for a specific type of property.
- 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_69aed9435cf48190ad1da737c962d19d |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc5087b081909d6042bfe8d8a306 |
completed | March 9, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69aef9082c2081908474f082a49bebc8 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:39 p.m.