Triple
T20801926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berliner Messe |
E512060
|
entity |
| Predicate | hasTitle |
P38
|
FINISHED |
| Object | Berliner Messe |
—
|
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: Berliner Messe | Statement: [Berliner Messe, hasTitle, Berliner Messe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berliner Messe Context triple: [Berliner Messe, hasTitle, Berliner Messe]
-
A.
Berliner Messe
chosen
Berliner Messe is a minimalist sacred choral composition by Estonian composer Arvo Pärt, written in his signature tintinnabuli style for the Latin Mass.
-
B.
Hannover Messe
Hannover Messe is one of the world’s largest and most influential industrial technology trade fairs, held annually in Hanover, Germany.
-
C.
Messe Berlin
Messe Berlin is a major exhibition and trade fair center in Berlin, Germany, hosting international trade shows, conferences, and large-scale events.
-
D.
Koelnmesse
Koelnmesse is a major international trade fair and exhibition company based in Cologne, Germany, known for organizing prominent events across various industries.
-
E.
Frankfurt Trade Fair
The Frankfurt Trade Fair is one of the world’s oldest and largest international trade fair venues, renowned for hosting major global exhibitions and industry events in Frankfurt, Germany.
- 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2b207c48190a9ca5895bdf85245 |
completed | April 21, 2026, 12:20 a.m. |
Created at: April 16, 2026, 12:39 p.m.