Triple
T22238467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Rivers |
E549653
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Rivers |
—
|
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: Rivers | Statement: [Mary Rivers, familyName, Rivers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rivers Context triple: [Mary Rivers, familyName, Rivers]
-
A.
Rivers
chosen
Rivers is a surname shared by various notable individuals across fields such as politics, sports, entertainment, and the arts.
-
B.
Streams
"Streams" is a jazz album by American saxophonist and composer Sam Rivers, showcasing his adventurous, avant-garde improvisational style.
-
C.
River
"River" is a novel by American author Roderick Thorp, best known for writing the book that inspired the film "Die Hard."
-
D.
River
River is a British crime drama television series created and written by Abi Morgan, centered on a troubled detective haunted by the visions of murder victims.
-
E.
River
"River" is a 2001 rock album by former Guns N' Roses guitarist Izzy Stradlin, noted for its laid-back, rootsy sound blending rock, blues, and Americana influences.
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f132123a048190ba5a90d7acb9aeb2 |
completed | April 28, 2026, 10:17 p.m. |
Created at: April 16, 2026, 8:38 p.m.