Triple
T9171731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manitoba Moose |
E220095
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | MB |
E73630
|
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: MB | Statement: [Manitoba Moose, abbreviation, MB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MB Context triple: [Manitoba Moose, abbreviation, MB]
-
A.
MB
chosen
MB is the official two-letter Canada Post abbreviation used to designate the province of Manitoba in mailing addresses and postal codes.
-
B.
MMB
MMB is the stock ticker symbol for Lagardère Group, a major French media and publishing conglomerate.
-
C.
MMB
MMB is the commonly used abbreviation for the Michigan Marching Band, the official marching band of the University of Michigan known for its performances at football games and major events.
-
D.
MBZ
MBZ is the widely used acronym for Mohamed bin Zayed Al Nahyan, the President of the United Arab Emirates and Ruler of Abu Dhabi.
-
E.
BM
BM is the regional vehicle registration code used on license plates for motor vehicles registered in Pekanbaru, Indonesia.
- 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_69ca83e467108190abcae6a33b3d4dad |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccaae38ee48190bf783477bc37913d |
completed | April 1, 2026, 5:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0549746b0819099c2a591900f9c8c |
completed | April 4, 2026, midnight |
Created at: March 30, 2026, 7:22 p.m.