Triple
T25186353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Jan Friedman |
E630728
|
entity |
| Predicate | hasWrittenNumberOfStarTrekBooks |
P5481
|
FINISHED |
| Object | more than 30 |
—
|
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: more than 30 | Statement: [Michael Jan Friedman, hasWrittenNumberOfStarTrekBooks, more than 30]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWrittenNumberOfStarTrekBooks Context triple: [Michael Jan Friedman, hasWrittenNumberOfStarTrekBooks, more than 30]
-
A.
hasNumberOfBooksInSeries
Indicates the quantity of books that belong to a particular series.
-
B.
numberOfBooks
chosen
Indicates the quantity of books associated with a given entity.
-
C.
numberOfCompletedBooks
Indicates the total count of books that an entity has finished reading or completing.
-
D.
appearsAcrossNumberOfNovels
Indicates the number of distinct novels in which a given entity makes an appearance.
-
E.
numberOfStarTrekEpisodesDirected
Indicates how many episodes of Star Trek a given person has directed.
- 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_69e75a8a6d088190ba1e82a4345225e7 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f46e0a26288190a51d138eef37a94a |
completed | May 1, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 12:44 p.m.