Triple
T20361691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antonin Dolohov |
E496794
|
entity |
| Predicate | escapedDuring |
P25285
|
FINISHED |
| Object | Mass Azkaban breakout of 1996 |
—
|
LITERAL 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: Mass Azkaban breakout of 1996 | Statement: [Antonin Dolohov, escapedDuring, Mass Azkaban breakout of 1996]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: escapedDuring Context triple: [Antonin Dolohov, escapedDuring, Mass Azkaban breakout of 1996]
-
A.
escapedBy
Indicates that an entity is freed or enabled to escape through the actions or intervention of another entity.
-
B.
trappedDuring
Indicates that one entity is confined, caught, or immobilized while a specified event or situation is occurring.
-
C.
fledDuring
chosen
Indicates that one entity escaped or ran away during the time period or event represented by the other entity.
-
D.
breachedDuring
Indicates that one entity violated, broke, or failed to uphold another entity (such as a rule, contract, or security measure) within a specified time period or event.
-
E.
escapeOutcome
Indicates the result or consequence of an attempt to escape, such as whether it succeeded, failed, or led to a particular follow-up state.
- F. None of above.
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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6786de5988190827584358c9db147 |
completed | April 20, 2026, 7:03 p.m. |
| PD | Predicate disambiguation | batch_69e57648be3c81908256838228cabf5c |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:25 a.m.