Triple
T10972465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Victor Frankenstein |
E259275
|
entity |
| Predicate | closeFriend |
P8712
|
FINISHED |
| Object | Henry Clerval |
E259346
|
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: Henry Clerval | Statement: [Victor Frankenstein, closeFriend, Henry Clerval]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Clerval Context triple: [Victor Frankenstein, closeFriend, Henry Clerval]
-
A.
Henry Clerval
chosen
Henry Clerval is Victor Frankenstein’s loyal and idealistic best friend whose compassion and humanism sharply contrast with Victor’s obsessive scientific ambition in Mary Shelley’s Frankenstein (1994 film).
-
B.
Alphonse Frankenstein
Alphonse Frankenstein is Victor Frankenstein’s compassionate and morally upright father in Mary Shelley’s novel "Frankenstein; or, The Modern Prometheus."
-
C.
Joseph von Franckenstein
Joseph von Franckenstein was an Austrian-born diplomat and writer best known as the husband of American author Kay Boyle.
-
D.
Victor
Victor is a central character in the TV series "Dollhouse," known as one of the programmable "Actives" whose identity and memories are repeatedly altered for various missions.
-
E.
Victor
Victor is a character in Gregory Benford’s science fiction novel "Timescape," which explores time communication and ecological catastrophe.
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7719b5edc81908c1019f81e78bd2e |
completed | April 9, 2026, 9:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2d7a0b3dc819084fbda3227caf5b5 |
completed | April 18, 2026, 1 a.m. |
Created at: April 8, 2026, 9:24 p.m.