Triple
T12802589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German mark |
E306058
|
entity |
| Predicate | replaced |
P101
|
FINISHED |
| Object | Thaler |
E223133
|
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: Thaler | Statement: [German mark, replaced, Thaler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thaler Context triple: [German mark, replaced, Thaler]
-
A.
Thaler
chosen
The Thaler was a large silver coin and monetary unit widely used across various German states and parts of Europe from the 16th to 19th centuries, serving as a precursor to the modern dollar.
-
B.
Thagard
Thagard is the surname of Norman E. Thagard, an American physician, former NASA astronaut, and the first American to fly on a Russian spacecraft.
-
C.
Laffer
Laffer is a surname most prominently associated with Arthur Laffer, the American economist known for the Laffer curve concept in supply-side economics.
-
D.
Blinder
Blinder is the NATO reporting name for the Soviet-era Tupolev Tu-22 supersonic bomber aircraft.
-
E.
Tobin
Tobin is the given name of Tobin Heath, an American professional soccer player and multiple-time FIFA Women's World Cup champion.
- 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_69d7bdf366888190a8cccb982606889c |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e7e3be48190ba9159c9f1ac2ccd |
completed | April 10, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68ec0d5dc819099a8036c6cbac634 |
completed | May 2, 2026, 11:54 p.m. |
Created at: April 9, 2026, 5:30 p.m.