Triple
T20226418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Exile |
E495392
|
entity |
| Predicate | followedBy |
P78
|
FINISHED |
| Object | Enigma |
—
|
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: Enigma | Statement: [Exile, followedBy, Enigma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Enigma Context triple: [Exile, followedBy, Enigma]
-
A.
Enigma
Enigma is a science fiction novel by Michael Kube-McDowell that explores complex themes of human identity, communication, and first contact.
-
B.
Enigma
Enigma is a 1982 Cold War spy thriller film involving codebreaking and espionage, directed by Jeannot Szwarc.
-
C.
Enigma
Enigma is a 2001 British World War II thriller film about codebreakers at Bletchley Park working to crack Nazi naval ciphers.
-
D.
Enigma
Enigma is a surreal, psychologically driven comic book miniseries that deconstructs superhero tropes and identity, written by Peter Milligan and originally published by Vertigo.
-
E.
Enigma
Enigma is a term most famously associated with the German cipher machine used during World War II for encrypted military communications.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69da626cff80819097b530718a7c98b6 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66fd9c1f4819092a98f5fa84fb795 |
completed | April 20, 2026, 6:26 p.m. |
Created at: April 11, 2026, 11:39 p.m.