Triple
T9102746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billie Jenkins |
E218397
|
entity |
| Predicate | allyOf |
P4662
|
FINISHED |
| Object | Paige Matthews |
E777942
|
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: Paige Matthews | Statement: [Billie Jenkins, allyOf, Paige Matthews]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paige Matthews Context triple: [Billie Jenkins, allyOf, Paige Matthews]
-
A.
Paige Matthews
chosen
Paige Matthews is a central witch character in the television series "Charmed," known as the half-sister who joins the Halliwell sisters to complete the Power of Three.
-
B.
Paige Meade
Paige Meade is an actress known for her role in the British science-fiction comedy film "Attack the Block."
-
C.
Paige Moss
Paige Moss is an American actress best known for her roles in 1990s teen films and television series, including a supporting role in the ensemble comedy "Can’t Hardly Wait."
-
D.
Paige Alexander
Paige Alexander is an American nonprofit leader and former U.S. government official who serves as the chief executive officer of The Carter Center.
-
E.
Paige Hurd
Paige Hurd is an American actress best known for her roles in television series such as "Everybody Hates Chris" and "The Oval," as well as various film appearances.
- 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_69ca83db7448819090d0a5de842ef2ac |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc9715d5188190bce68d095e10c2eb |
completed | April 1, 2026, 3:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d030201a048190a3a1166d23c5ae67 |
completed | April 3, 2026, 9:24 p.m. |
Created at: March 30, 2026, 7:15 p.m.