Triple
T11016871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Duff |
E260386
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Duff's device |
E900227
|
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: Duff's device | Statement: [Tom Duff, notableWork, Duff's device]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Duff's device Context triple: [Tom Duff, notableWork, Duff's device]
-
A.
Duff's device
chosen
Duff's device is a loop-unrolling technique in the C programming language that exploits switch-case fall-through to optimize data copying, famously demonstrating an unusual and clever use of C's control structures.
-
B.
Marzullo's algorithm
Marzullo's algorithm is a method for selecting the most likely correct time interval from multiple, possibly conflicting time sources, commonly used in clock synchronization systems.
-
C.
Duff
Duff is a masculine given name of Scottish origin, traditionally derived from a Gaelic word meaning "dark" or "swarthy."
-
D.
Duff
Duff is a common nickname used by British rail enthusiasts for the British Rail Class 47 diesel-electric locomotive.
-
E.
M4 macro processor
The M4 macro processor is a general-purpose macro processing language and tool commonly used in Unix-like systems for generating and transforming text, especially in build and configuration workflows.
- 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_69d6aa9687448190b28d353b1b6a610e |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d797a682908190b061d1995e2866b6 |
completed | April 9, 2026, 12:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3a98725808190903639866a3e745f |
completed | April 18, 2026, 3:55 p.m. |
Created at: April 8, 2026, 9:25 p.m.