Triple
T14484655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cordelia |
E359194
|
entity |
| Predicate | enemy |
P4567
|
FINISHED |
| Object | Regan |
E359759
|
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: Regan | Statement: [Cordelia, enemy, Regan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Regan Context triple: [Cordelia, enemy, Regan]
-
A.
Regan
chosen
Regan is one of King Lear’s daughters in Shakespeare’s tragedy, known for her cruelty, ambition, and betrayal.
-
B.
Regan
Regan is a surname most notably associated with Michael S. Regan, the American environmental regulator and current Administrator of the U.S. Environmental Protection Agency.
-
C.
Raegan
Raegan is a given name, typically a modern variant of the name Reagan, used for both girls and boys.
-
D.
Belle Avery
Belle Avery is a film producer best known for developing and producing the science fiction shark thriller "The Meg."
-
E.
Kathleen
Kathleen is a feminine given name of Irish origin, derived from the name Catherine and widely used in English-speaking countries.
- 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924d7f4c8190b1f62b5ffe1ff649 |
completed | April 14, 2026, 7:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd6d8f1bf081908c37f8f41767b382 |
completed | May 8, 2026, 4:58 a.m. |
Created at: April 10, 2026, 1:20 a.m.