Triple
T14509541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UM |
E340358
|
entity |
| Predicate | represents |
P129
|
FINISHED |
| Object | MRU |
E301522
|
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: MRU | Statement: [UM, represents, MRU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MRU Context triple: [UM, represents, MRU]
-
A.
MRU
MRU is the three-letter ISO 4217 currency code for the Mauritanian ouguiya, the official currency of Mauritania.
-
B.
MRU
chosen
MRU is the abbreviation for the Mano River Union, a regional organization that promotes economic cooperation and integration among West African countries along the Mano River.
-
C.
MRIT
MRIT is an abbreviation for the Matsushita Research Institute Tokyo, a Japanese research organization historically associated with Panasonic’s advanced technology and electronics R&D.
-
D.
MRIA
MRIA is the post-nominal title indicating membership of the Royal Irish Academy, an all-Ireland body of distinguished scholars and scientists.
-
E.
MRIA
MRIA is the abbreviation for Mattala Rajapaksa International Airport, a major international airport located in southern Sri Lanka.
- 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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de94e5b7b48190878be271840c265b |
completed | April 14, 2026, 7:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd7a4660c881908d0cdc27c277ae6b |
completed | May 8, 2026, 5:53 a.m. |
Created at: April 10, 2026, 1:21 a.m.