Triple
T7412644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drenthe |
E171047
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Hunebedden |
E132428
|
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: Hunebedden | Statement: [Drenthe, contains, Hunebedden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hunebedden Context triple: [Drenthe, contains, Hunebedden]
-
A.
Hunebedden
chosen
Hunebedden are prehistoric megalithic tombs built from large boulders by Neolithic farming communities in what is now the Netherlands.
-
B.
Hellenstein ruins
The Hellenstein ruins are the remains of a historic hilltop castle complex overlooking Heidenheim an der Brenz in southern Germany.
-
C.
Brandbergen
Brandbergen is a residential district and suburb located within Haninge Municipality in the Stockholm County region of Sweden.
-
D.
Barkeval
Barkeval is a prominent mountain peak on the Isle of Rùm in Scotland’s Inner Hebrides, forming part of the rugged Rum Cuillin range.
-
E.
Gravensteen castle
Gravensteen castle is a well-preserved medieval fortress in Ghent, Belgium, known for its imposing stone walls, towers, and historical exhibits.
- 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_69c68a618bdc81908d8018edadecd1a4 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f2a027148190bdb6a7940389e377 |
completed | March 27, 2026, 9:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8112960d48190a9947146e62daa13 |
completed | March 28, 2026, 5:34 p.m. |
Created at: March 27, 2026, 3:11 p.m.