Triple
T22498956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ISRG |
E556217
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Eric Rescorla |
—
|
NE NERFINISHED |
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: Eric Rescorla | Statement: [ISRG, foundedBy, Eric Rescorla]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eric Rescorla Context triple: [ISRG, foundedBy, Eric Rescorla]
-
A.
Eric Rescorla
chosen
Eric Rescorla is a computer security expert and software engineer best known as a key designer of the Transport Layer Security (TLS) protocol and a leading contributor to Internet security standards.
-
B.
Paul Mowrer
Paul Mowrer was an American journalist and foreign correspondent who won the first Pulitzer Prize for foreign correspondence in 1929.
-
C.
Richard M. Shiffrin
Richard M. Shiffrin is a prominent cognitive psychologist renowned for his influential theories and models of human memory and attention.
-
D.
Jack Grossberg
Jack Grossberg is a film producer best known for his work on Woody Allen’s 1973 science-fiction comedy "Sleeper."
-
E.
Bruce D. Lucas
Bruce D. Lucas is a computer scientist best known for co-developing the Lucas–Kanade method, a foundational algorithm in computer vision for estimating optical flow and image alignment.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e5445bc8190b6a9481926db3355 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15cb3deb88190874230ae06a352d6 |
completed | April 29, 2026, 1:19 a.m. |
Created at: April 16, 2026, 8:50 p.m.