Triple
T17027852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Town of Basel |
E413112
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Barfüsserplatz |
—
|
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: Barfüsserplatz | Statement: [Old Town of Basel, contains, Barfüsserplatz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Barfüsserplatz Context triple: [Old Town of Basel, contains, Barfüsserplatz]
-
A.
Barfüsserplatz
chosen
Barfüsserplatz is a central public square in Basel, Switzerland, known as a major tram hub and venue for markets and city events.
-
B.
Margaretenplatz
Margaretenplatz is a notable public square in Vienna’s Margareten district, known for its local shops, cafes, and neighborhood atmosphere.
-
C.
Matthäikirchplatz
Matthäikirchplatz is a public square within Berlin’s Kulturforum complex, serving as an open space framed by major cultural institutions and the St. Matthew’s Church.
-
D.
Walther-Schreiber-Platz
Walther-Schreiber-Platz is an underground station on Berlin’s U-Bahn network, serving the U9 line in the southwestern part of the city.
-
E.
Georgenkirchplatz
Georgenkirchplatz is a former name for a historic square in central Berlin, Germany, now known as Hackescher Markt.
- 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d728148190b83367cd6fdefa50 |
completed | April 18, 2026, 7:04 p.m. |
Created at: April 10, 2026, 5:33 a.m.