Triple
T5312117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Tale of Tom Kitten |
E119054
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Tabitha Twitchit |
E510294
|
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: Tabitha Twitchit | Statement: [The Tale of Tom Kitten, featuresCharacter, Tabitha Twitchit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tabitha Twitchit Context triple: [The Tale of Tom Kitten, featuresCharacter, Tabitha Twitchit]
-
A.
Tabitha Twitchit
chosen
Tabitha Twitchit is a mother cat character from Beatrix Potter’s children’s stories, known for her prim, proper, and somewhat fussy demeanor.
-
B.
Tabitha
Tabitha is a feminine given name of Aramaic origin, traditionally interpreted to mean "gazelle" and associated with grace and beauty.
-
C.
Tabitha King
Tabitha King is an American author known for her novels and short stories, and as the wife of writer Stephen King.
-
D.
Tabitha Grant
Tabitha Grant is the daughter of British actor Hugh Grant and his former partner Tinglan Hong.
-
E.
Tabitha Lenox
Tabitha Lenox is a powerful and mischievous witch from the soap opera "Passions," known for her dark magic, eccentric personality, and close bond with her doll-turned-sidekick, Timmy.
- 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_69bd446b57bc8190a513d2e6c40314f3 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd8535a1ec819094b2c5d3cfc57f56 |
completed | March 20, 2026, 5:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf188988688190b4b08b5e0cda8cf5 |
completed | March 21, 2026, 10:15 p.m. |
Created at: March 20, 2026, 1:54 p.m.