Triple
T22173722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johannistor@de |
E547987
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | string "Johannistor" |
—
|
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: string "Johannistor" | Statement: [Johannistor@de, hasPart, string "Johannistor"]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: string "Johannistor" Context triple: [Johannistor@de, hasPart, string "Johannistor"]
-
A.
Johannistor@de
chosen
Johannistor@de is the German-language designation of the historical city gate known as the Johannistor.
-
B.
Johannitsa
Johannitsa was a medieval Bulgarian ruler better known as Kaloyan, the tsar who significantly expanded the Second Bulgarian Empire in the early 13th century.
-
C.
Johanniskirche
Johanniskirche is a historic church in the German town of Schwäbisch Gmünd, notable for its medieval architecture and cultural significance.
-
D.
Johannsson
Johannsson is a character in August Strindberg’s expressionist play "The Ghost Sonata," contributing to its eerie, dreamlike exploration of guilt and illusion.
-
E.
Johanneskirchen
Johanneskirchen is a residential district in the northeastern part of Munich, Germany, known for its mix of housing, green spaces, and S-Bahn connectivity.
- 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_69e11e3d53f88190a2b690e3f25bb062 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12a6a9370819098ad65fede676c2b |
completed | April 28, 2026, 9:45 p.m. |
Created at: April 16, 2026, 8:34 p.m.