Triple
T12341882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Konrad Zuse |
E294244
|
entity |
| Predicate | designed |
P184
|
FINISHED |
| Object |
Z64 Graphomat
The Z64 Graphomat is an early computer-controlled plotter developed in the 1950s that automated the precise drawing of technical diagrams and graphics.
|
E978854
|
NE FINISHED |
How this triple was built (4 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: Z64 Graphomat | Statement: [Konrad Zuse, designed, Z64 Graphomat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Z64 Graphomat Context triple: [Konrad Zuse, designed, Z64 Graphomat]
-
A.
GR-64
GR-64 is the ISO 3166-2 regional code assigned to the Chalkidiki regional unit in Greece.
-
B.
Z 6400
Z 6400 is a class of French electric multiple unit trains operated by SNCF for suburban commuter services around Paris.
-
C.
NuMachine
NuMachine was an early 1980s experimental workstation computer project at MIT that pioneered the NuBus expansion bus architecture.
-
D.
Ngizmawa
Ngizmawa is an alternative name for the Ngizim people, an ethnic group primarily found in northeastern Nigeria.
-
E.
Z3
Z3 is a high-performance theorem prover and SMT (Satisfiability Modulo Theories) solver developed by Microsoft Research, widely used in formal verification, program analysis, and automated reasoning.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Z64 Graphomat Triple: [Konrad Zuse, designed, Z64 Graphomat]
Generated description
The Z64 Graphomat is an early computer-controlled plotter developed in the 1950s that automated the precise drawing of technical diagrams and graphics.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Z64 Graphomat Target entity description: The Z64 Graphomat is an early computer-controlled plotter developed in the 1950s that automated the precise drawing of technical diagrams and graphics.
-
A.
GR-64
GR-64 is the ISO 3166-2 regional code assigned to the Chalkidiki regional unit in Greece.
-
B.
Z 6400
Z 6400 is a class of French electric multiple unit trains operated by SNCF for suburban commuter services around Paris.
-
C.
NuMachine
NuMachine was an early 1980s experimental workstation computer project at MIT that pioneered the NuBus expansion bus architecture.
-
D.
Ngizmawa
Ngizmawa is an alternative name for the Ngizim people, an ethnic group primarily found in northeastern Nigeria.
-
E.
Z3
Z3 is a high-performance theorem prover and SMT (Satisfiability Modulo Theories) solver developed by Microsoft Research, widely used in formal verification, program analysis, and automated reasoning.
- F. None of above. chosen
Provenance (5 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f7758dc8190bbc6a9ad00b01dce |
completed | April 10, 2026, 6:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62aaa1d548190be065412aab70385 |
completed | May 2, 2026, 4:47 p.m. |
| NEDg | Description generation | batch_69f62c55aacc8190a0544306825bdfab |
completed | May 2, 2026, 4:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f62d51ab8081909c6f534051019dca |
completed | May 2, 2026, 4:58 p.m. |
Created at: April 8, 2026, 9:53 p.m.