Triple
T15938363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TUDM |
E386495
|
entity |
| Predicate | hasAcronym |
P43
|
FINISHED |
| Object | TUDM |
E386495
|
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: TUDM | Statement: [TUDM, hasAcronym, TUDM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TUDM Context triple: [TUDM, hasAcronym, TUDM]
-
A.
TUDM
chosen
TUDM is the Malay-language abbreviation for the Royal Malaysian Air Force, the aerial warfare branch of Malaysia’s armed forces.
-
B.
TUDN
TUDN is a Spanish-language sports television network and media brand focused on soccer and other sports, primarily serving audiences in the United States and Mexico.
-
C.
TUDMB
TUDMB is the marching band of Temple University, known for its high-energy performances at athletic events and university functions.
-
D.
TUDa
TUDa is a leading German research university located in Darmstadt, renowned for its engineering, computer science, and natural sciences programs.
-
E.
TMDU
TMDU is the commonly used abbreviation for Tokyo Medical and Dental University, a leading Japanese national university specializing in medical and dental education and research.
- 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_69d86da750008190987eb26be3f6c118 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156ac934c8190b6178eb66023252e |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe7455c48190bfad24eb8905426d |
completed | May 9, 2026, 11:08 p.m. |
Created at: April 10, 2026, 4:53 a.m.