Triple
T285016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman legion |
E5868
|
entity |
| Predicate | hasServiceTerm |
P2920
|
FINISHED |
| Object | typically 20 to 25 years |
—
|
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: typically 20 to 25 years | Statement: [Roman legion, hasServiceTerm, typically 20 to 25 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasServiceTerm Context triple: [Roman legion, hasServiceTerm, typically 20 to 25 years]
-
A.
hasServiceTo
Indicates that one entity provides, offers, or operates a service for or directed toward another entity.
-
B.
hasSurvivorTerm
Indicates that an entity is associated with a term or label specifically used to describe survivors of an event, condition, or circumstance.
-
C.
hasTerm
chosen
Indicates that an entity includes, is associated with, or is defined by a specific term or condition.
-
D.
hasFormerService
Indicates that an entity previously provided a service to another entity but no longer does so.
-
E.
servedByService
Indicates that something is provided, handled, or fulfilled by a particular service.
- 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_69a25946a7ac8190a78871c210213272 |
completed | Feb. 28, 2026, 2:56 a.m. |
| NER | Named-entity recognition | batch_69a2605b372c8190831570aa6532cc96 |
completed | Feb. 28, 2026, 3:26 a.m. |
| PD | Predicate disambiguation | batch_69a25b7a8d148190aacdcc8ccb35c7f3 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 3:02 a.m.