Triple
T19421243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franekeradeel |
E485857
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Firdgum |
—
|
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: Firdgum | Statement: [Franekeradeel, contains, Firdgum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Firdgum Context triple: [Franekeradeel, contains, Firdgum]
-
A.
Firdgum
chosen
Firdgum is a small village in the Dutch province of Friesland, known for its historic terp (artificial dwelling mound) landscape.
-
B.
Dargun
Dargun is a small town in northeastern Germany known for its historic monastery and castle complex set amid the rural lake and hill landscape of Mecklenburg.
-
C.
Dernau
Dernau is a small wine-growing village in Germany’s Ahr Valley, renowned for its vineyards and scenic river landscape.
-
D.
Farenthold
Farenthold is the surname of a Texas political family most notably associated with former U.S. Representative Blake Farenthold.
-
E.
Gnafron
Gnafron is a traditional comic character from the Lyonnais Guignol puppet theatre, typically portrayed as Guignol’s jovial, wine-loving cobbler friend.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63214d768819082129100d7116521 |
completed | April 20, 2026, 2:03 p.m. |
Created at: April 10, 2026, 1:37 p.m.