Triple
T4993950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annie Costner |
E112198
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Grace Costner |
E115584
|
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: Grace Costner | Statement: [Annie Costner, sibling, Grace Costner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grace Costner Context triple: [Annie Costner, sibling, Grace Costner]
-
A.
Grace Costner
chosen
Grace Costner is one of American actor and filmmaker Kevin Costner’s daughters.
-
B.
Cindy Costner
Cindy Costner is an American actress and former wife of actor Kevin Costner, known for small roles in films such as "Dances with Wolves."
-
C.
Annie Costner
Annie Costner is an American film producer and occasional actress, best known as the daughter of actor and filmmaker Kevin Costner.
-
D.
Lucinda Jenney
Lucinda Jenney is an American character actress known for her versatile supporting roles in films and television since the 1980s.
-
E.
Tyne Daly
Tyne Daly is an American actress acclaimed for her powerful performances in television dramas, film, and theater, including her iconic role in the series "Cagney & Lacey."
- 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_69bd4432b32c81909f3b3c6bd10f0653 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd729d3d448190a414a003a75104f6 |
completed | March 20, 2026, 4:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bea470ca3c81909e24b18e1e609dbd |
completed | March 21, 2026, 2 p.m. |
Created at: March 20, 2026, 1:34 p.m.