Triple
T6281140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LEMD |
E140783
|
entity |
| Predicate | associatedWithIATA |
P12360
|
FINISHED |
| Object | MAD |
E140782
|
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: MAD | Statement: [LEMD, associatedWithIATA, MAD]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MAD Context triple: [LEMD, associatedWithIATA, MAD]
-
A.
MAD
chosen
MAD is the three-letter IATA airport code for Adolfo Suárez Madrid–Barajas Airport, the main international airport serving Madrid, Spain.
-
B.
MAD
MAD is a museum dedicated to contemporary art and design, showcasing innovative and experimental works across various media.
-
C.
U Mad
"U Mad" is a hip-hop single by American rapper Vic Mensa featuring Kanye West, known for its aggressive energy and confrontational lyrics.
-
D.
MDA
MDA (Monochrome Display Adapter) is IBM's original text-only video display standard for early IBM PCs, providing high-resolution monochrome output without graphics capabilities.
-
E.
MDA
MDA is a Canadian space technology company known for developing advanced satellite systems, robotics, and Earth observation solutions.
- 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_69c008cd17c8819082b82d3fbeb68047 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063dee62881908347283f16dcbe68 |
completed | March 22, 2026, 9:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c5e411332481908ffff37cad062cce |
completed | March 27, 2026, 1:57 a.m. |
Created at: March 22, 2026, 4:26 p.m.