Triple
T21277646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orlando |
E524431
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Roland |
—
|
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: Roland | Statement: [Orlando, basedOn, Roland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roland Context triple: [Orlando, basedOn, Roland]
-
A.
Roland
chosen
Roland is a masculine given name of Germanic origin, historically associated with the legendary Frankish hero of "The Song of Roland" and later borne by various notable figures.
-
B.
Roland Gift
Roland Gift is a British singer, songwriter, and actor best known as the lead vocalist of the Fine Young Cannibals.
-
C.
Rolland
Rolland is a given name and surname, most commonly recognized as a variant spelling of Roland used in various European and English-speaking contexts.
-
D.
Karle
Karle is a surname most notably associated with Jerome Karle, the American physical chemist and Nobel Prize laureate.
-
E.
Rolland Hein
Rolland Hein is an American literary scholar and professor best known for his work on Christian literature and the writings of George MacDonald.
- 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_69e0b516293c819089458ea2ec85f85e |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e736583c08819087a4726538e703e2 |
completed | April 21, 2026, 8:33 a.m. |
Created at: April 16, 2026, 4:02 p.m.