Triple
T19504017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pennsylvania State Police |
E487973
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Mounted Unit |
—
|
NE NERFINISHED |
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: Mounted Unit | Statement: [Pennsylvania State Police, hasPart, Mounted Unit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mounted Unit Context triple: [Pennsylvania State Police, hasPart, Mounted Unit]
-
A.
Mounted Unit
chosen
The Mounted Unit is a specialized police division whose officers patrol on horseback to enhance crowd control, visibility, and community engagement in urban environments.
-
B.
C-Unit
C-Unit is the official student cheering section for the University of Colorado Boulder’s Buffaloes football team, known for its energetic support at home games.
-
C.
Mobile Unit
Mobile Unit is a touring theater program of The Public Theater that brings free, professional performances to underserved communities and nontraditional venues.
-
D.
Unit 101
Unit 101 was an elite Israeli special forces unit formed in the early 1950s, known for its cross-border reprisal operations and for being led by future Prime Minister Ariel Sharon.
-
E.
Assembled
"Assembled" is an Overwatch animated short that expands the game's lore by showcasing its characters and world through high-quality cinematic storytelling.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e635105db8819084915dc2d047188d |
completed | April 20, 2026, 2:15 p.m. |
Created at: April 10, 2026, 1:40 p.m.