Triple
T23821239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Sergeant |
E589242
|
entity |
| Predicate | typicalUnitLevel |
P118085
|
FINISHED |
| Object | company |
—
|
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: company | Statement: [First Sergeant, typicalUnitLevel, company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalUnitLevel Context triple: [First Sergeant, typicalUnitLevel, company]
-
A.
typicalEquipmentLevel
Indicates the usual or standard amount or quality of equipment associated with an entity or situation.
-
B.
typicalHighestLevel
Indicates the usual or most common maximum level or degree that something typically reaches within a given context.
-
C.
typicalLowestLevel
Indicates that something represents the most basic or minimal level that is commonly or normally found within a given context.
-
D.
hasUnitLevel
chosen
Indicates that something is associated with, measured at, or applicable to a specific unit level within a larger hierarchy or scale.
-
E.
typicalExperienceLevel
Indicates the usual or most common level of experience associated with an entity in a given context.
- 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_69e25d18619081909c7fb89d8926f14a |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c7af4d4481908095348fae9e54f4 |
completed | April 29, 2026, 8:56 a.m. |
| PD | Predicate disambiguation | batch_69f156036ad48190bc2ffdaf39218bcb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:59 p.m.