Triple
T18593223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tara Thornton |
E454421
|
entity |
| Predicate | closeFriendOf |
P8712
|
FINISHED |
| Object | Sookie Stackhouse |
E447628
|
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: Sookie Stackhouse | Statement: [Tara Thornton, closeFriendOf, Sookie Stackhouse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sookie Stackhouse Context triple: [Tara Thornton, closeFriendOf, Sookie Stackhouse]
-
A.
Sookie Stackhouse
chosen
Sookie Stackhouse is a telepathic waitress from Louisiana and the central heroine of Charlaine Harris’s Southern Vampire Mysteries novels and their TV adaptation, True Blood.
-
B.
Sookie St. James
Sookie St. James is a quirky, warm-hearted chef and Lorelai Gilmore’s best friend in the television series "Gilmore Girls."
-
C.
Adele Stackhouse
Adele Stackhouse is Sookie Stackhouse’s kind, open-minded grandmother and a beloved matriarchal figure in Charlaine Harris’s Southern Vampire Mysteries series.
-
D.
Mayce
Mayce is the first name of former NBA All-Star and Hall of Fame power forward Chris Webber.
-
E.
Amariah Faulkner
Amariah Faulkner is a Canadian actress and voice performer known for her roles in animated television series and films.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e545b7ce3881908302ee27a2cf80d6 |
completed | April 19, 2026, 9:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a04f89b0cd88190bee76c1f78368c22 |
completed | May 13, 2026, 10:18 p.m. |
Created at: April 10, 2026, 11:44 a.m.