Triple
T96805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minutemen |
E1949
|
entity |
| Predicate | trainingLevel |
P4144
|
FINISHED |
| Object | higher than average colonial militia |
—
|
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: higher than average colonial militia | Statement: [Minutemen, trainingLevel, higher than average colonial militia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trainingLevel Context triple: [Minutemen, trainingLevel, higher than average colonial militia]
-
A.
difficulty
Indicates the level of challenge, complexity, or effort required to perform an action, solve a problem, or achieve a particular outcome.
-
B.
competitionLevel
Indicates the degree or intensity of competitive pressure or rivalry present in a given context or interaction.
-
C.
technologyLevel
Indicates the degree of technological advancement or sophistication associated with an entity relative to others or to a defined scale.
-
D.
orderGradeLevel
Indicates the relative sequencing or ranking of grade levels, specifying which grade comes before or after another.
-
E.
trainingGround
Indicates a location or context where entities engage in practice, drills, or preparation activities to develop or improve skills.
- 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_69a24d4862f881908cc8b89d3a78031d |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a250cb400c8190b56343bbe19b48c7 |
completed | Feb. 28, 2026, 2:19 a.m. |
| PD | Predicate disambiguation | batch_69a24ebd19c48190bab291fea0ecc0c2 |
completed | Feb. 28, 2026, 2:11 a.m. |
| PDg | Predicate description generation | batch_69a250ca7eec8190b31f7e61f5e3ee1f |
completed | Feb. 28, 2026, 2:19 a.m. |
Created at: Feb. 28, 2026, 2:09 a.m.