Triple
T18829050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Act II of The Relapse |
E460472
|
entity |
| Predicate | hasCharacter |
P2308
|
FINISHED |
| Object | Amanda |
—
|
NE NERFINISHED |
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: Amanda | Statement: [Act II of The Relapse, hasCharacter, Amanda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amanda Context triple: [Act II of The Relapse, hasCharacter, Amanda]
-
A.
Amanda
chosen
Amanda is the central character of the work "The Relapse," around whom the main events and conflicts of the story revolve.
-
B.
Amanda
"Amanda" is a song by the American punk rock band Green Day from their album ¡Tré!.
-
C.
Amanda
Amanda is a feminine given name of Latin origin, meaning "worthy of love" or "lovable."
-
D.
Amanda
Amanda is the assumed identity of the main character Emily Thorne in the television series "Revenge."
-
E.
Amanda
Amanda is a character in the Swedish novel "Drottningens juvelsmycke" ("The Queen's Tiara"), a classic work of 19th-century literature by Carl Jonas Love Almqvist.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a99554848190933dd2810f5c810f |
completed | April 20, 2026, 4:20 a.m. |
Created at: April 10, 2026, 11:56 a.m.