Triple
T4868045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Favourite Game |
E109018
|
entity |
| Predicate | followsInAuthorCareer |
P57383
|
FINISHED |
| Object | Leonard Cohen’s early poetry collections |
—
|
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: Leonard Cohen’s early poetry collections | Statement: [The Favourite Game, followsInAuthorCareer, Leonard Cohen’s early poetry collections]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsInAuthorCareer Context triple: [The Favourite Game, followsInAuthorCareer, Leonard Cohen’s early poetry collections]
-
A.
followsWorkOfAuthor
Indicates that one entity continues, builds upon, or is influenced by the work previously produced by a specified author.
-
B.
followedByRoleInCareerOf
Indicates that one role or position directly succeeds another in the sequence of roles within a single entity’s career.
-
C.
workInAuthorCareer
Indicates that an author’s professional work or role occurs within and is part of their overall writing career.
-
D.
followsInBibliography
Indicates that one bibliographic entry directly succeeds another in the ordering of a bibliography or reference list.
-
E.
workInChronologyOfAuthor
chosen
Indicates that a work appears within, and is ordered as part of, the chronological sequence of an author's creations or publications.
- 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_69bd440d96a48190b0c87069adef2af1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d7bb0b88190bbc24498619910fc |
completed | March 20, 2026, 3:53 p.m. |
| PD | Predicate disambiguation | batch_69bd6c27334481909ba8ac80854f7d8e |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:26 p.m.