Triple
T22183516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Marx |
E548231
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Erdberg |
—
|
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: Erdberg | Statement: [St. Marx, locatedNear, Erdberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erdberg Context triple: [St. Marx, locatedNear, Erdberg]
-
A.
Erdberg
chosen
Erdberg is a neighborhood in Vienna’s 3rd district, known for its major transport hubs and mix of residential and commercial areas.
-
B.
Ytterkollen
Ytterkollen is a small village in Norway that forms part of the former municipality of Nedre Eiker in Viken county.
-
C.
Ytteren
Ytteren is a residential village in Nordland county, Norway, situated near the town of Mo i Rana within Rana Municipality.
-
D.
Eggerberg
Eggerberg is a small Swiss municipality in the canton of Valais, known for its hillside location above the Rhône valley and views of the surrounding Alps.
-
E.
Erkheim
Erkheim is a small municipality in the Unterallgäu district of Bavaria in southern 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_69e11e3e0c7c8190b30d278845e2497e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12aa687808190b9959d4e91db948a |
completed | April 28, 2026, 9:46 p.m. |
Created at: April 16, 2026, 8:35 p.m.