Triple
T34795396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Thomas and Lady Jane |
E1003062
|
entity |
| Predicate | partOfSeriesOfDraftsFor |
P202200
|
FINISHED |
| Object | Lady Chatterley’s Lover |
—
|
NE NERFINISHED |
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: Lady Chatterley’s Lover | Statement: [John Thomas and Lady Jane, partOfSeriesOfDraftsFor, Lady Chatterley’s Lover]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfSeriesOfDraftsFor Context triple: [John Thomas and Lady Jane, partOfSeriesOfDraftsFor, Lady Chatterley’s Lover]
-
A.
draftsFrom
Indicates a relationship where one item is created, derived, or composed as a draft based on another source item.
-
B.
presentedDraftTo
Indicates that one entity has shown or submitted a draft version of something to another entity for their review, consideration, or approval.
-
C.
hasDraft
Indicates that one entity possesses or is associated with a preliminary or unfinished version of another entity.
-
D.
draftingSupervisedBy
Indicates that the drafting of a document or work product is carried out under the supervision or oversight of a specified person or authority.
-
E.
hasDraftRelationshipWith
Indicates a provisional or not-yet-finalized relationship exists between two entities.
- F. None of above. chosen
Provenance (4 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a0061454944819088a0babfe60f69fc |
completed | May 10, 2026, 10:43 a.m. |
| PD | Predicate disambiguation | batch_6a0060b9ee108190b91e8d99a16f2b30 |
completed | May 10, 2026, 10:40 a.m. |
| PDg | Predicate description generation | batch_6a0061448f6881908daa9fb0da9abefe |
completed | May 10, 2026, 10:43 a.m. |
Created at: May 3, 2026, 3:59 p.m.