Triple
T12063476
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Viterbi |
E287233
|
entity |
| Predicate | knownFor |
P22
|
FINISHED |
| Object | Viterbi algorithm |
E252270
|
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: Viterbi algorithm | Statement: [Andrew Viterbi, knownFor, Viterbi algorithm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Viterbi algorithm Context triple: [Andrew Viterbi, knownFor, Viterbi algorithm]
-
A.
Viterbi algorithm
chosen
The Viterbi algorithm is a dynamic programming method used to find the most likely sequence of hidden states in probabilistic models such as Hidden Markov Models, widely applied in fields like digital communications, speech recognition, and bioinformatics.
-
B.
Viterbi
Viterbi is a surname most prominently associated with Andrew Viterbi, the Italian-American engineer and co-inventor of the Viterbi algorithm used in digital communications and error correction.
-
C.
Baum–Welch algorithm
The Baum–Welch algorithm is an expectation-maximization method used to train the parameters of hidden Markov models from observed data.
-
D.
forward-backward algorithm
The forward-backward algorithm is a dynamic programming method for computing posterior state probabilities in hidden Markov models, widely used in tasks like sequence labeling and speech recognition.
-
E.
Hidden Markov Model
A Hidden Markov Model is a statistical model that represents systems with unobserved (hidden) states generating observable outputs, widely used for sequence analysis tasks such as speech recognition, bioinformatics, and natural language processing.
- 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_69d6ab4846e081908ee7bbd66a6d3459 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d90440dd988190ae2b80367aceb6f7 |
completed | April 10, 2026, 2:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e3ee53c81909c2e4620a12a46da |
completed | May 2, 2026, 3:54 p.m. |
Created at: April 8, 2026, 9:48 p.m.