Triple
T8362277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Mifflin |
E197036
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Mifflin |
E63348
|
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: Mifflin | Statement: [Thomas Mifflin, familyName, Mifflin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mifflin Context triple: [Thomas Mifflin, familyName, Mifflin]
-
A.
Mifflin
chosen
Mifflin is the middle name of George M. Dallas, the 11th vice president of the United States.
-
B.
Finklea
Finklea is the birth surname of American actress and dancer Cyd Charisse, known for her roles in classic Hollywood musicals.
-
C.
Merrill
Merrill is a surname most notably associated with American actor Gary Merrill, known for his work in mid-20th-century film and television.
-
D.
Merrill
Merrill is the wealth management and brokerage division of Bank of America, offering investment advice, financial planning, and related services to individual and institutional clients.
-
E.
Merrill
Merrill is a given name used by various notable individuals across fields such as literature, entertainment, and business.
- 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_69ca82f2dbe48190aba982e75a0d94de |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb8074e4588190b394d1622adca2cb |
completed | March 31, 2026, 8:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc77cf2ac8190a1c5b618fd64da73 |
completed | April 2, 2026, 1:33 a.m. |
Created at: March 30, 2026, 6 p.m.