Triple
T20639342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spearhead |
E507178
|
entity |
| Predicate | appliesToTypeOfUnit |
P140872
|
FINISHED |
| Object | armored division |
—
|
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: armored division | Statement: [Spearhead, appliesToTypeOfUnit, armored division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToTypeOfUnit Context triple: [Spearhead, appliesToTypeOfUnit, armored division]
-
A.
governsTypeOfUnit
Indicates that one entity has authority or control over the type or category of unit to which another entity belongs.
-
B.
hasUnitOf
Indicates that a quantity, measurement, or value is expressed in terms of a specific unit.
-
C.
isAUnitOf
Indicates that one entity functions as a unit or standard measure in which the other entity is quantified or expressed.
-
D.
appliesToProductType
Indicates that something (such as a rule, offer, or condition) is relevant or applicable specifically to a certain type or category of product.
-
E.
typeOfUnit
Indicates that one entity specifies the kind or category of measurement unit that the other entity belongs to.
- 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_69e0b4be702c8190a3d2410a881d310a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6ad126b6481908d4e235bd73dda2e |
completed | April 20, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69e5a0155bd48190b3c769a12cc2c83d |
completed | April 20, 2026, 3:40 a.m. |
| PDg | Predicate description generation | batch_69e5a6a9f3f88190b961db9aca36f7da |
completed | April 20, 2026, 4:08 a.m. |
Created at: April 16, 2026, 11:42 a.m.