Triple
T23233629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Satellite Terminal of T4 |
E581227
|
entity |
| Predicate | airportCode |
P418
|
FINISHED |
| Object | MAD |
—
|
NE NERFINISHED |
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: [Satellite Terminal of T4, airportCode, MAD]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MAD Context triple: [Satellite Terminal of T4, airportCode, 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.
MAD
MAD is a long-running American humor magazine famous for its satirical takes on popular culture, politics, and everyday life.
-
D.
MAD
MAD is Germany’s military counterintelligence service responsible for protecting the armed forces from espionage, sabotage, and extremist threats.
-
E.
M.A.D.
M.A.D. is the nefarious criminal organization led by the villain Dr. Claw in the animated series "Inspector Gadget."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2460556f88190be1744a84a84173f |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192e70b2c8190abede6e3cd9344f7 |
completed | April 29, 2026, 5:11 a.m. |
Created at: April 17, 2026, 4:09 p.m.