Triple
T20102769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosemarie Trockel |
E496587
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Trockel |
—
|
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: Trockel | Statement: [Rosemarie Trockel, familyName, Trockel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trockel Context triple: [Rosemarie Trockel, familyName, Trockel]
-
A.
Trockel
chosen
Trockel is the surname of Rosemarie Trockel, a prominent German conceptual artist known for her innovative textile and multimedia works.
-
B.
Trocka
Trocka is a Warsaw Metro station serving the Targówek district in Poland.
-
C.
Trappier
Trappier is a French surname most notably associated with Éric Trappier, the CEO of Dassault Aviation.
-
D.
Trost
Trost is a surname most notably associated with Barry M. Trost, an influential American chemist known for his work in organic synthesis and the concept of atom economy.
-
E.
Trockener Steg
Trockener Steg is a high-altitude mountain station and ski area hub above Zermatt, Switzerland, serving as a key junction for cable cars and access to the surrounding glaciers and peaks.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6667170a4819085d07a4188ded541 |
completed | April 20, 2026, 5:46 p.m. |
Created at: April 11, 2026, 11:27 p.m.