Triple
T17260287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanya Donelly |
E418990
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Donelly |
E1178100
|
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: Donelly | Statement: [Tanya Donelly, familyName, Donelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donelly Context triple: [Tanya Donelly, familyName, Donelly]
-
A.
Delaney
Delaney is a surname of Irish origin commonly borne by individuals and families in English-speaking countries.
-
B.
Delly
Delly is the nickname of Australian professional basketball player Matthew Dellavedova, known for his gritty defense and tenure in the NBA, including a championship run with the Cleveland Cavaliers.
-
C.
Denninger
Denninger is a German-origin surname borne by various individuals, including the American actor Richard Denning.
-
D.
Dodie
Dodie is the nickname of English novelist and playwright Dodie Smith, best known as the author of "The Hundred and One Dalmatians" and "I Capture the Castle."
-
E.
Donnelly
chosen
Donnelly is an Irish-origin surname commonly associated with families of Gaelic heritage and found widely in Ireland and the Irish diaspora.
- 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_69d886d9ab108190b70edd8d17aa1204 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e6fa940819089046d1b12dede2c |
completed | April 19, 2026, 1:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a017101d5dc8190ac6507344897b0f3 |
completed | May 11, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:39 a.m.