Triple
T17032472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Turku Art Museum |
E413232
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Puolalanmäki hill |
E1247900
|
NE FINISHED |
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: Puolalanmäki hill | Statement: [Turku Art Museum, locatedOn, Puolalanmäki hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Puolalanmäki hill Context triple: [Turku Art Museum, locatedOn, Puolalanmäki hill]
-
A.
Puolalanmäki hill
chosen
Puolalanmäki hill is a prominent elevated area in central Turku, Finland, known for its park-like surroundings and cultural landmarks.
-
B.
Leivonmäki
Leivonmäki is a former rural municipality in Central Finland known for its forests, lakes, and the Leivonmäki National Park.
-
C.
Haapamäki
Haapamäki is a village in Keuruu, Finland, known as a historic railway junction and hub in the Finnish rail network.
-
D.
Alm-Öhi
Alm-Öhi is the elderly, reclusive goat herder and grandfather of Heidi in Johanna Spyri’s classic Swiss children’s novel "Heidi."
-
E.
Emi Koussi
Emi Koussi is a massive extinct volcano in northern Chad that forms the highest peak in the Sahara Desert.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d8ed79448190a750a29a99913fda |
completed | April 18, 2026, 7:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012ed2ad708190a250762997611569 |
completed | May 11, 2026, 1:20 a.m. |
Created at: April 10, 2026, 5:33 a.m.