Triple
T26947695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dorothy is shipwrecked on her way to Australia |
E678690
|
entity |
| Predicate | relatedWorkFollows |
P9710
|
FINISHED |
| Object | Dorothy and the Wizard in Oz |
—
|
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: Dorothy and the Wizard in Oz | Statement: [Dorothy is shipwrecked on her way to Australia, relatedWorkFollows, Dorothy and the Wizard in Oz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedWorkFollows Context triple: [Dorothy is shipwrecked on her way to Australia, relatedWorkFollows, Dorothy and the Wizard in Oz]
-
A.
relatedWorkBySubject
Indicates a relationship where one work is connected to another through sharing the same subject or topic.
-
B.
followsWork
chosen
Indicates that one work (such as a publication, version, or creative piece) comes directly after another in sequence or succession.
-
C.
relatedWorkByAttribution
Indicates that one work is connected to another through explicit attribution, such as citation, acknowledgment, or credit given by the creator or source.
-
D.
relatedWorkOfPerson
Indicates that a work (such as a publication, project, or creation) is associated with or produced by a particular person.
-
E.
relatedWorkForm
Indicates a relationship in which one work is connected to another through a different form or version (e.g., adaptation, translation, or other format variation).
- 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_69eeeb4d69588190a7c912164a1c37b3 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69ff0b6bc4a88190bf1d38c6ea26bcdc |
completed | May 9, 2026, 10:24 a.m. |
| PD | Predicate disambiguation | batch_69ff082a22f4819095ded971dbd8ea7b |
completed | May 9, 2026, 10:10 a.m. |
Created at: April 27, 2026, 6:22 a.m.