Triple
T21082923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tall John |
E519414
|
entity |
| Predicate | hasNameInSwedish |
P11737
|
FINISHED |
| Object | Långe Jan |
—
|
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: Långe Jan | Statement: [Tall John, hasNameInSwedish, Långe Jan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Långe Jan Context triple: [Tall John, hasNameInSwedish, Långe Jan]
-
A.
Långe Jan
chosen
Långe Jan is Sweden’s tallest lighthouse, located at the southern tip of the Baltic Sea island of Öland.
-
B.
Lange Jan
Lange Jan is a famous tall church tower in Middelburg, the Netherlands, known as one of the country’s most prominent landmarks.
-
C.
Ole-Johan
Ole-Johan is the given name of Ole-Johan Dahl, a pioneering Norwegian computer scientist known for co-developing object-oriented programming.
-
D.
Långe Erik
Långe Erik is a historic lighthouse located on the northern tip of the island Öland in Sweden, known as a counterpart to the southern lighthouse Långe Jan.
-
E.
Sjøholt
Sjøholt is a small coastal village in Møre og Romsdal county in western Norway, known for its scenic fjord landscape and proximity to major transport routes.
- 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_69e0b506e59c8190849b71ed07929215 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e702dcbf9c81908e4cc016eb21bbbc |
completed | April 21, 2026, 4:53 a.m. |
Created at: April 16, 2026, 2:49 p.m.