Triple
T3839184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Innenstadt (Frankfurt am Main) |
E93408
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Alte Oper |
E95590
|
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: Alte Oper | Statement: [Innenstadt (Frankfurt am Main), hasLandmark, Alte Oper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alte Oper Context triple: [Innenstadt (Frankfurt am Main), hasLandmark, Alte Oper]
-
A.
Alte Oper
chosen
Alte Oper is a historic former opera house in Frankfurt am Main that now serves as a prominent concert and event venue.
-
B.
Romanian National Opera
The Romanian National Opera is a major opera and ballet company and cultural landmark based in Bucharest, renowned for its classical repertoire and performances.
-
C.
Vienna State Opera
The Vienna State Opera is one of the world’s leading opera houses, renowned for its rich history, prestigious productions, and central role in Vienna’s classical music culture.
-
D.
Cuvilliés Theatre
Cuvilliés Theatre is an ornate 18th-century Rococo court theatre in Munich, renowned as one of Europe’s finest surviving examples of Baroque theatre architecture.
-
E.
Opernhaus
Opernhaus is an underground rapid transit station on the Nuremberg U-Bahn network in Nuremberg, Germany.
- 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_69aed96ce578819084ab16e3439976c9 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeeb9f305c8190b71ac53bbb0c4beb |
completed | March 9, 2026, 3:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51228a7a48190bc42898be15b450b |
completed | March 14, 2026, 7:45 a.m. |
Created at: March 9, 2026, 3:18 p.m.