Triple
T19889664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs Lyons |
E477993
|
entity |
| Predicate | tellsLie |
P110172
|
FINISHED |
| Object | twins who are separated will die if they find out the truth |
—
|
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: twins who are separated will die if they find out the truth | Statement: [Mrs Lyons, tellsLie, twins who are separated will die if they find out the truth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tellsLie Context triple: [Mrs Lyons, tellsLie, twins who are separated will die if they find out the truth]
-
A.
liesUpon
Indicates that one entity is positioned resting directly on the surface of another entity.
-
B.
liesToThe
chosen
Indicates that one entity intentionally provides false or misleading information to another entity.
-
C.
tells
Indicates that one entity communicates information, a message, or a story to another entity.
-
D.
hasLie
Indicates that an entity is associated with or responsible for a specific lie or false statement.
-
E.
speaksTruthWhen
Indicates that the subject tells the truth under the specified conditions or in relation to the referenced entity or situation.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6590ce9f48190a51c0e5ecc828a06 |
completed | April 20, 2026, 4:49 p.m. |
| PD | Predicate disambiguation | batch_69e537ecda248190895c96afb6243823 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:52 p.m.