Triple
T15909712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs. George |
E385813
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Kylie George |
E1183717
|
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: Kylie George | Statement: [Mrs. George, child, Kylie George]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kylie George Context triple: [Mrs. George, child, Kylie George]
-
A.
Kylie George
chosen
Kylie George is a lesser-known sibling of the fictional character Regina George from the film "Mean Girls."
-
B.
Kylie Rogers
Kylie Rogers is an American actress best known for her lead role as the young girl in the faith-based drama film "Miracles from Heaven."
-
C.
Kylie Dodson
Kylie Dodson is an individual associated with the use of something referred to as "Dodson," though little public information is available about her beyond this connection.
-
D.
Kylie Peppler
Kylie Peppler is a learning sciences researcher known for her work on creative computing, maker education, and the integration of arts and technology in STEM learning.
-
E.
Kylie du Fresne
Kylie du Fresne is an Australian film and television producer known for her work on acclaimed independent features and series.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1565ea7a8819097efffda366b5245 |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe6e844481908227ec9e46ac9f4d |
completed | May 9, 2026, 11:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.