Triple
T973654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mounted Unit |
E21000
|
entity |
| Predicate | isTypicallyPartOf |
P35
|
FINISHED |
| Object | municipal police department |
—
|
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: municipal police department | Statement: [Mounted Unit, isTypicallyPartOf, municipal police department]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isTypicallyPartOf Context triple: [Mounted Unit, isTypicallyPartOf, municipal police department]
-
A.
hasPartIn
Indicates that an entity participates in or plays a role within a larger event, process, or composite entity.
-
B.
isPartOfType
Indicates that one type or category is a constituent or subset within a larger, encompassing type or category.
-
C.
isNotPartOf
Indicates that one entity does not belong to, is not contained within, and is not a component or member of another entity.
-
D.
hasPart
chosen
Indicates that one entity is a component, segment, or constituent part of another entity.
-
E.
isAssociatedWith
Indicates that there exists a connection, relationship, or involvement between two entities without specifying its exact nature.
- 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_69a493c2b62c8190b616351789ec47f8 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b45f28f081908d41b2d7f353708d |
completed | March 1, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69a4b2a6aa2c8190aebba71320ab678f |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.