Triple
T18661419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Holmwood |
E456205
|
entity |
| Predicate | alignmentBeforeTransformation |
P26427
|
FINISHED |
| Object | innocent |
—
|
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: innocent | Statement: [Lucy Holmwood, alignmentBeforeTransformation, innocent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alignmentBeforeTransformation Context triple: [Lucy Holmwood, alignmentBeforeTransformation, innocent]
-
A.
alignmentShape
Indicates that one entity’s shape is arranged, oriented, or matched in position relative to another entity’s shape.
-
B.
alignmentGoal
Indicates that an entity has a desired or target alignment state it aims to achieve or maintain.
-
C.
alignmentComponents
Indicates that one entity is composed of or associated with specific subparts or elements that together form its overall alignment.
-
D.
previousAlignment
chosen
Indicates that one entity’s alignment or orientation occurred earlier in time than another’s.
-
E.
alignmentMethod
Indicates the technique or procedure used to align one entity with another or with a reference standard.
- 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_69d8d38f72b4819090a935175d9ca8af |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5508a30248190abdb51e345168849 |
completed | April 19, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69e478db7a248190a8c6584673773923 |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:48 a.m.