Triple
T10687306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glenda Farrell |
E251911
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Farrell |
E769706
|
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: Farrell | Statement: [Glenda Farrell, familyName, Farrell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Farrell Context triple: [Glenda Farrell, familyName, Farrell]
-
A.
Farrell
chosen
Farrell is a surname of Irish origin borne by numerous notable individuals across fields such as entertainment, sports, and politics.
-
B.
Farley
Farley is a rural-residential suburb in the Maitland region of New South Wales, Australia.
-
C.
Farley
Farley is a surname most notably associated with Jim Farley, an American business executive and CEO of Ford Motor Company.
-
D.
Rafferty
Rafferty is an English model and actor best known as the son of actor Jude Law and actress Sadie Frost.
-
E.
Fonzarelli
Fonzarelli is the surname of Arthur "Fonzie" Fonzarelli, the iconic leather-jacket-wearing greaser from the American TV sitcom "Happy Days."
- 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_69d6aa5bd7c08190a816e733b4045c23 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fd19f0f481909eeaa75d17d9c060 |
completed | April 9, 2026, 1:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98894cea48190877a015dcb645bee |
completed | April 10, 2026, 11:32 p.m. |
Created at: April 8, 2026, 9:10 p.m.