Triple
T5507798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Franciscus |
E144485
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Mr. Novak |
E322877
|
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: Mr. Novak | Statement: [James Franciscus, notableWork, Mr. Novak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mr. Novak Context triple: [James Franciscus, notableWork, Mr. Novak]
-
A.
Mr. Franks
Mr. Franks is a music producer best known for his work with the hip-hop collective Legend.
-
B.
John Norville
John Norville is a screenwriter best known for co-writing the story for Disney's adventure film "Jungle Cruise."
-
C.
William Novak
chosen
William Novak is an American writer and ghostwriter best known for co-authoring high-profile political and celebrity memoirs.
-
D.
Marvin Krislov
Marvin Krislov is an American academic leader and former president of Oberlin College who serves as the president of Pace University in New York.
-
E.
Stanley Mazor
Stanley Mazor is an American computer engineer best known as one of the key designers of the first commercial microprocessor and an early pioneer in microprocessor architecture at Intel.
- 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_69c008f6b5048190a09064116062cf69 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f495c588190b0cfe5bfb3d2c221 |
completed | March 22, 2026, 4:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c027c082108190a3c8f826a6aeef4c |
completed | March 22, 2026, 5:32 p.m. |
Created at: March 22, 2026, 3:32 p.m.