Triple
T1056191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Karp |
E22800
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | David Karp |
E22800
|
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: David Karp | Statement: [David Karp, name, David Karp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Karp Context triple: [David Karp, name, David Karp]
-
A.
David Karp
chosen
David Karp is an American web developer and entrepreneur best known for creating the microblogging platform Tumblr.
-
B.
Matthew Freund
Matthew Freund is a film editor known for his work on the comedy movie "Fist Fight."
-
C.
Ryan Roslansky
Ryan Roslansky is the CEO of LinkedIn, known for leading the professional networking platform’s product and business strategy.
-
D.
Chris Day
Chris Day is a British academic and medical researcher who serves as the Vice-Chancellor and President of Newcastle University.
-
E.
Richard Appel
Richard Appel is an American television writer and producer best known for his work on animated series such as The Simpsons, King of the Hill, and Family Guy.
- 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_69a493dada0481909c43649f9843ea91 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b8d9102c819090af78cae50f0ff2 |
completed | March 1, 2026, 10:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac3bd110ac8190b66163de42bd3034 |
completed | March 7, 2026, 2:53 p.m. |
Created at: March 1, 2026, 7:42 p.m.