Triple
T16046985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Stamatina Fey |
E389246
|
entity |
| Predicate | hasFamilyName |
P18
|
FINISHED |
| Object | Fey |
E82146
|
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: Fey | Statement: [Elizabeth Stamatina Fey, hasFamilyName, Fey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fey Context triple: [Elizabeth Stamatina Fey, hasFamilyName, Fey]
-
A.
Fey
chosen
Fey is the surname of American comedian, writer, actress, and producer Tina Fey, known for her work on "Saturday Night Live" and "30 Rock."
-
B.
Feydey
Feydey is a small locality in the Swiss Alps near Leysin, known primarily as a residential and resort area within the Vaud canton.
-
C.
Faerie
Faerie is a vast, magical otherworld of enchantment, danger, and ancient powers that serves as the primary fantastical realm in Neil Gaiman’s novel "Stardust."
-
D.
Feyli
Feyli is a dialect of Southern Kurdish spoken primarily by the Feyli Kurds in parts of Iraq and Iran.
-
E.
Ferae
Ferae is a mammalian clade that primarily includes carnivorans (such as dogs, cats, and bears) and pangolins, reflecting a close evolutionary relationship between these groups.
- 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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1835eda348190aff492f0ff668cce |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbddc25481908fca660c4f14eaff |
completed | May 10, 2026, 1:14 a.m. |
Created at: April 10, 2026, 4:56 a.m.