Triple
T3945878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ENIAC project |
E92145
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | ENIAC |
E92145
|
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: ENIAC | Statement: [ENIAC project, hasPart, ENIAC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ENIAC Context triple: [ENIAC project, hasPart, ENIAC]
-
A.
EDVAC
EDVAC was one of the earliest electronic stored-program computers, pioneering the use of binary arithmetic and influencing the development of modern computer architecture.
-
B.
UNIVAC I
UNIVAC I was one of the earliest commercial electronic computers, pioneering large-scale data processing for government and business in the early 1950s.
-
C.
ENIAC project
chosen
The ENIAC project was an early U.S. military-funded effort during World War II to develop one of the first general-purpose electronic digital computers, laying foundational concepts for modern computing.
-
D.
Colossus computers
Colossus computers were pioneering British electronic computing machines built during World War II to help decrypt high-level German communications at Bletchley Park.
-
E.
IBM 650
The IBM 650 was an early, widely used mid-1950s drum-based decimal computer that helped popularize electronic data processing in business and education.
- 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_69aed965502c8190904ebad1203a4ae8 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef0da13688190aab505c36513e4ab |
completed | March 9, 2026, 4:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5339869fc8190aee0805a8e2deac5 |
completed | March 14, 2026, 10:08 a.m. |
Created at: March 9, 2026, 3:24 p.m.