Triple
T19481580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lincoln Lee |
E487396
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Lincoln Lee |
—
|
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: Lincoln Lee | Statement: [Lincoln Lee, hasName, Lincoln Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lincoln Lee Context triple: [Lincoln Lee, hasName, Lincoln Lee]
-
A.
Lincoln Lee
chosen
Lincoln Lee is a character from the science fiction TV series "Fringe," known as an FBI agent who appears in both the prime and parallel universes with differing personalities.
-
B.
Lincoln Lyons
Lincoln Lyons is the child of Rosie Lyons, a character in the British television drama "Years and Years."
-
C.
Lincoln Murphy
Lincoln Murphy is a customer success strategist and author known for his influential work on SaaS growth and customer-centric business practices.
-
D.
Lewis Lee
Lewis Lee is the family name shared by American producer and advocate Tonya Lewis Lee and her relatives, including her husband, filmmaker Spike Lee.
-
E.
Hancock Lee
Hancock Lee was a colonial Virginian planter and politician from the prominent Lee family of Virginia.
- 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e634393b8081909f5e4c38b2f1a9b7 |
completed | April 20, 2026, 2:12 p.m. |
Created at: April 10, 2026, 1:39 p.m.