Triple
T16262741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Follo region |
E394793
|
entity |
| Predicate | containsMunicipality |
P852
|
FINISHED |
| Object | Ski |
E245864
|
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: Ski | Statement: [Follo region, containsMunicipality, Ski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ski Context triple: [Follo region, containsMunicipality, Ski]
-
A.
Ski
chosen
Ski is a town in Viken county, Norway, serving as a regional commercial and transport hub southeast of Oslo.
-
B.
Ski
Ski is an American hip-hop record producer best known for his work with artists like Jay-Z and Camp Lo during the 1990s.
-
C.
Esquías
Esquías is a town and municipality located in the Comayagua Department of central Honduras.
-
D.
KitzSki
KitzSki is a major Austrian ski resort area renowned for its extensive slopes, modern lift system, and the famous Hahnenkamm downhill race.
-
E.
Telemark skiing
Telemark skiing is a skiing discipline that combines elements of alpine and Nordic skiing, characterized by a free-heel binding and a distinctive lunging turn technique.
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245c5583c8190901e892238cf8dbd |
completed | April 17, 2026, 2:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017b5f3a8819083128cf2b90cfd84 |
completed | May 10, 2026, 5:29 a.m. |
Created at: April 10, 2026, 5:04 a.m.