Triple
T28889631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Captain of the White Tower |
E732660
|
entity |
| Predicate | appearsInAppendicesOf |
P180788
|
FINISHED |
| Object | The Lord of the Rings |
—
|
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: The Lord of the Rings | Statement: [Captain of the White Tower, appearsInAppendicesOf, The Lord of the Rings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appearsInAppendicesOf Context triple: [Captain of the White Tower, appearsInAppendicesOf, The Lord of the Rings]
-
A.
appearsIn
Indicates that an entity is present, featured, or occurs within a particular context, work, or medium.
-
B.
appendicesCount
Indicates the number of appendices associated with a given entity or document.
-
C.
appearsInBookNumber
Indicates that an entity is featured or mentioned in a specific book identified by its number within a series or collection.
-
D.
hasAppendix
Indicates that one entity includes or is associated with an appendix section related to another entity.
-
E.
isRevealedIn
Indicates that something becomes known, disclosed, or made apparent within a particular context, medium, or situation.
- 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_69f05b07bdec819080cadfe147aa1f25 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f7516d5b4081908588a6feb541f355 |
completed | May 3, 2026, 1:45 p.m. |
| PD | Predicate disambiguation | batch_69f74d40ebb081909daf60623e38f41d |
completed | May 3, 2026, 1:27 p.m. |
| PDg | Predicate description generation | batch_69f7516c538481908c6e55cf76add098 |
completed | May 3, 2026, 1:45 p.m. |
Created at: April 28, 2026, 7:54 a.m.