Triple
T10739949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Errol Flynn |
E253295
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Arnella Flynn |
E253302
|
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: Arnella Flynn | Statement: [Errol Flynn, hasChild, Arnella Flynn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arnella Flynn Context triple: [Errol Flynn, hasChild, Arnella Flynn]
-
A.
Arnella Flynn
chosen
Arnella Flynn was the daughter of famed Hollywood swashbuckling actor Errol Flynn.
-
B.
Mercedes Kilmer
Mercedes Kilmer is an American actress and the daughter of actor Val Kilmer, known for roles in independent films such as "Ingrid Goes West" and "Paydirt."
-
C.
Miriam Flynn
Miriam Flynn is an American actress and voice artist best known for her comedic roles in film and television, including her work in the National Lampoon franchise.
-
D.
Lindsay Bluth Fünke
Lindsay Bluth Fünke is a vain, materialistic, and often clueless member of the dysfunctional Bluth family on the television sitcom "Arrested Development."
-
E.
Rhea Seehorn
Rhea Seehorn is an American actress best known for her critically acclaimed role as attorney Kim Wexler on the television series "Better Call Saul."
- 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_69d6aa5e51e8819095f06881cecf152e |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d71043106c819091939950f532eda5 |
completed | April 9, 2026, 2:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de22ed6edc8190beb76bd2971c7cec |
completed | April 14, 2026, 11:20 a.m. |
Created at: April 8, 2026, 9:14 p.m.