Triple
T20909164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mannheim City Airport |
E514890
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object |
EDFM
EDFM is the ICAO airport code for Mannheim City Airport, a regional airport serving the city of Mannheim in southwestern Germany.
|
E1457082
|
NE FINISHED |
How this triple was built (4 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: EDFM | Statement: [Mannheim City Airport, ICAOcode, EDFM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: EDFM Context triple: [Mannheim City Airport, ICAOcode, EDFM]
-
A.
EDFE
EDFE is the ICAO airport code for Frankfurt Egelsbach Airport, a general aviation airfield near Frankfurt, Germany.
-
B.
EDFH
EDFH is the ICAO airport code for Hahn Air Base, a former U.S. military airfield in Germany now used as a civilian airport.
-
C.
EFM
EFM (Ethernet in the First Mile) is a networking standard that extends Ethernet technology to connect service providers to customer premises over the access network.
-
D.
EFM
EFM is a major international film industry marketplace held annually alongside the Berlin International Film Festival, where producers, distributors, and buyers trade and promote films and audiovisual content.
-
E.
EDC
EDC is a massive electronic dance music festival known for its elaborate stages, immersive art installations, and carnival-like atmosphere.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: EDFM Triple: [Mannheim City Airport, ICAOcode, EDFM]
Generated description
EDFM is the ICAO airport code for Mannheim City Airport, a regional airport serving the city of Mannheim in southwestern Germany.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: EDFM Target entity description: EDFM is the ICAO airport code for Mannheim City Airport, a regional airport serving the city of Mannheim in southwestern Germany.
-
A.
EDFE
EDFE is the ICAO airport code for Frankfurt Egelsbach Airport, a general aviation airfield near Frankfurt, Germany.
-
B.
EDFH
EDFH is the ICAO airport code for Hahn Air Base, a former U.S. military airfield in Germany now used as a civilian airport.
-
C.
EFM
EFM (Ethernet in the First Mile) is a networking standard that extends Ethernet technology to connect service providers to customer premises over the access network.
-
D.
EFM
EFM is a major international film industry marketplace held annually alongside the Berlin International Film Festival, where producers, distributors, and buyers trade and promote films and audiovisual content.
-
E.
EDC
EDC is a massive electronic dance music festival known for its elaborate stages, immersive art installations, and carnival-like atmosphere.
- F. None of above. chosen
Provenance (5 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_69e0b4f8a1108190bce3d31331290ced |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6e901ca50819080b123af7977efbd |
completed | April 21, 2026, 3:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0918dc2f9481908a7364ce25f11eb0 |
completed | May 17, 2026, 1:24 a.m. |
| NEDg | Description generation | batch_6a091bee5e3c8190adc31821815f7878 |
completed | May 17, 2026, 1:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a091c9c47048190be29a12c1d074d98 |
completed | May 17, 2026, 1:40 a.m. |
Created at: April 16, 2026, 12:48 p.m.