Triple
T17957175
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Wedloe |
E448982
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Wedloe |
—
|
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: Wedloe | Statement: [Tom Wedloe, familyName, Wedloe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wedloe Context triple: [Tom Wedloe, familyName, Wedloe]
-
A.
Wedloe
chosen
Wedloe is a surname most notably associated with the fictional character Mark Wedloe from the television series "Gentle Ben."
-
B.
Freneau
Freneau is the surname of Philip Freneau, an American poet often called the "Poet of the American Revolution."
-
C.
Pinckney
Pinckney is a given name of English origin historically used in the United States, notably borne by figures such as early American politicians and military leaders.
-
D.
Coxe
Coxe is a surname variant of Cox, borne by various individuals across history and regions.
-
E.
the Franklin
The Franklin is a wealthy, hospitable landowner and storyteller in Geoffrey Chaucer’s *The Canterbury Tales*, known for narrating “The Franklin’s Tale.”
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4afb0afe08190964e771ec632fa1e |
completed | April 19, 2026, 10:34 a.m. |
Created at: April 10, 2026, 10:21 a.m.