Triple
T3281570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady Lazarus |
E68882
|
entity |
| Predicate | placeInAuthorCareer |
P19243
|
FINISHED |
| Object | late work |
—
|
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: late work | Statement: [Lady Lazarus, placeInAuthorCareer, late work]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: placeInAuthorCareer Context triple: [Lady Lazarus, placeInAuthorCareer, late work]
-
A.
workInAuthorCareer
Indicates that an author’s professional work or role occurs within and is part of their overall writing career.
-
B.
authorOccupation
Indicates the professional role or job that an author holds or is associated with.
-
C.
partOfCareer
chosen
Indicates that one entity represents a role, position, or period that forms a component or phase within another entity’s overall career.
-
D.
managedCareerOf
Indicates that one entity was responsible for overseeing, directing, or handling the professional career of another entity.
-
E.
placeAssociatedWithAuthor
Indicates a relationship where a place is connected to an author, such as by birth, residence, work, or significant activity.
- 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_69ad859c463481909ca4be267336c290 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb032d76c81909c568a4e56d12ce9 |
completed | March 8, 2026, 5:21 p.m. |
| PD | Predicate disambiguation | batch_69ada420167c81909b6e2702db296d9e |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:10 p.m.