Triple
T7678068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Midnight Run |
E173915
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | UP 200 |
E173914
|
NE 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: UP 200 | Statement: [Midnight Run, associatedWith, UP 200]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UP 200 Context triple: [Midnight Run, associatedWith, UP 200]
-
A.
UP 200
chosen
UP 200 is a prominent mid-distance sled dog race held annually in Michigan’s Upper Peninsula, attracting mushers and teams from across North America.
-
B.
UPG
UPG is the IATA airport code for Sultan Hasanuddin International Airport serving Makassar in South Sulawesi, Indonesia.
-
C.
UPP
UPP is a reporting mark used by the Union Pacific Railroad to identify certain passenger cars and related rolling stock in its fleet.
-
D.
UP-W
UP-W is the service designation used by Metra for its Union Pacific West commuter rail line in the Chicago metropolitan area.
-
E.
UPPT
UPPT is an acronym commonly used to refer to the Uniformed Personnel Performance Team, a group focused on assessing and enhancing the effectiveness of uniformed staff.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c6995703e0819081de77361b602e78 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c701fd18d88190888144a7d0f228d9 |
completed | March 27, 2026, 10:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8ac9af1c081908b0e100390258eaa |
completed | March 29, 2026, 4:37 a.m. |
Created at: March 27, 2026, 4:01 p.m.