Triple
T22763810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paizo Publishing |
E563064
|
entity |
| Predicate | keyPerson |
P256
|
FINISHED |
| Object | Lisa Stevens |
—
|
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: Lisa Stevens | Statement: [Paizo Publishing, keyPerson, Lisa Stevens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lisa Stevens Context triple: [Paizo Publishing, keyPerson, Lisa Stevens]
-
A.
Lisa Stevens
Lisa Stevens is a songwriter known for her work on the hit song "Holiday."
-
B.
Lisa Stevens
chosen
Lisa Stevens is a prominent figure in the tabletop role-playing game industry, best known as the founder of Paizo Publishing and for her influential work on brands like Dungeons & Dragons and Pathfinder.
-
C.
Mary Stevens
Mary Stevens was the wife of prominent American lawyer and politician Robert R. Livingston, a key figure in early United States history.
-
D.
Mary Stevens
Mary Stevens is a fictional character from the television series "Zapped," known for being one of the key figures in the show's comedic fantasy setting.
-
E.
Lisa Stewart
Lisa Stewart is a film producer best known for her work on the acclaimed coming-of-age movie "Almost Famous."
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a7f56848190b5e90f9916a5b349 |
completed | April 29, 2026, 3:26 a.m. |
Created at: April 17, 2026, 3:26 p.m.