Triple
T8982182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richard Marden |
E214557
|
entity |
| Predicate | hasFamilyName |
P18
|
FINISHED |
| Object | Marden |
E549095
|
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: Marden | Statement: [Richard Marden, hasFamilyName, Marden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marden Context triple: [Richard Marden, hasFamilyName, Marden]
-
A.
Marden
chosen
Marden is a surname most notably associated with the American minimalist painter Brice Marden.
-
B.
Mortain
Mortain is a town in Normandy, France, known as the focal point of a major German counteroffensive during the Battle of Normandy in World War II.
-
C.
Manton
Manton is a small unincorporated community located in Nelson County, Kentucky, known for its rural setting within the state's central region.
-
D.
Manton
Manton is a small unincorporated rural community in Tehama County, California, known for its agricultural setting and proximity to the Cascade Range foothills.
-
E.
Manton
Manton is a neighborhood and village area located within Providence County in the state of Rhode Island.
- 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_69ca839ea8b88190922c6a326ffcc0d3 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc67a891e881909e4b84ed82491651 |
completed | April 1, 2026, 12:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc97617908190859d1e27248f43cf |
completed | April 3, 2026, 2:06 p.m. |
Created at: March 30, 2026, 7:03 p.m.