Triple
T17141597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kurt Tank |
E415977
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Tank |
E415977
|
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: Tank | Statement: [Kurt Tank, familyName, Tank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tank Context triple: [Kurt Tank, familyName, Tank]
-
A.
Tank
Tank is a London-based art and fashion magazine known for its independent, avant-garde editorial approach and collaborations with experimental cultural projects.
-
B.
Tank
chosen
Tank is a German aeronautical engineer best known for designing the Focke-Wulf Fw 190 fighter aircraft used by the Luftwaffe during World War II.
-
C.
Tank
Tank is an American R&B singer, songwriter, and producer known for his smooth vocals and hit slow jams like "Maybe I Deserve" and "Please Don't Go."
-
D.
Tank
Tank is a town in Pakistan’s Khyber Pakhtunkhwa province, known as the administrative center of Tank District near the Gomal River.
-
E.
Tank God
Tank God is a hip-hop and trap music producer best known for his work with Post Malone, including contributions to the album "Beerbongs & Bentleys."
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f2d5de10819090cbd65661b018d3 |
completed | April 18, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a014154b9848190ac01602eb01ae710 |
completed | May 11, 2026, 2:39 a.m. |
Created at: April 10, 2026, 5:36 a.m.