Triple
T20439918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feldkirch |
E501355
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object | Tisis |
—
|
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: Tisis | Statement: [Feldkirch, hasSubdivision, Tisis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tisis Context triple: [Feldkirch, hasSubdivision, Tisis]
-
A.
Tisis
chosen
Tisis is a district of the Austrian city of Feldkirch, located near the Swiss border in the state of Vorarlberg.
-
B.
Tayshet
Tayshet is a town in Irkutsk Oblast, Russia, known as a major railway junction in Siberia.
-
C.
Nisaea
Nisaea was the port town and harbor of ancient Megara in Greece, serving as its main maritime outlet on the Saronic Gulf.
-
D.
Ziria
Ziria is a mountain in the northeastern Peloponnese of Greece, traditionally identified with Mount Cyllene, which is famed in Greek mythology as the birthplace of the god Hermes.
-
E.
Tirico
Tirico is the surname of American sportscaster Mike Tirico, known for his play-by-play work on major sports broadcasts.
- 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_69e0b4ab3cfc8190ac9bf32e932316b1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e685f20fe08190b9370b523a20153d |
completed | April 20, 2026, 8 p.m. |
Created at: April 16, 2026, 11:31 a.m.