Triple
T3041405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oberharz am Brocken |
E83137
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Tanne |
E320360
|
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: Tanne | Statement: [Oberharz am Brocken, hasPart, Tanne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tanne Context triple: [Oberharz am Brocken, hasPart, Tanne]
-
A.
Tanne
chosen
Tanne is a small village in the Harz region of central Germany, now part of the town of Oberharz am Brocken.
-
B.
Birch
Birch is a masculine given name most notably borne by American politician Birch Bayh, a long-serving U.S. senator from Indiana.
-
C.
Mountain Ash
Mountain Ash is a former coal-mining town and community in the Cynon Valley of Rhondda Cynon Taf, South Wales.
-
D.
Kedr
Kedr was the radio call sign used by Yuri Gagarin during his historic Vostok 1 mission, the first human spaceflight.
-
E.
Figtree
Figtree is a residential suburb of Wollongong in New South Wales, Australia, known for its shopping centre and proximity to both the Illawarra escarpment and the city centre.
- 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_69ad8b2298908190a7cb4e9bdbf064d0 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9b5b92088190971bed04e65c5917 |
completed | March 8, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1eef191ec8190a28c8beec31fffd1 |
completed | March 11, 2026, 10:38 p.m. |
Created at: March 8, 2026, 3:01 p.m.