Triple
T21895776
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tiki Barber |
E540674
|
entity |
| Predicate | coWroteSeries |
P47055
|
FINISHED |
| Object | children's books about football |
—
|
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: children's books about football | Statement: [Tiki Barber, coWroteSeries, children's books about football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coWroteSeries Context triple: [Tiki Barber, coWroteSeries, children's books about football]
-
A.
wroteTelevisionSeriesFor
Indicates that one entity is the writer or creator of the script or content for a particular television series for another entity (such as a network, studio, or production).
-
B.
coAuthorAlsoWrote
Indicates that a person who is a co-author of one work also wrote another work, linking shared authorship across multiple creations.
-
C.
hasWritingCreditOn
chosen
Indicates that an entity is credited as a writer or co-writer for a particular work or production.
-
D.
workWrittenFor
Indicates that a creative work was specifically composed, produced, or created for a particular person, group, event, purpose, or medium.
-
E.
hasAuthorOf
Indicates that one entity is the author or creator of another entity (such as a work, document, or publication).
- 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_69e0c47a95908190ae3e19b716accb3d |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fc6062c81908bf0aad7c6b99932 |
completed | April 28, 2026, 8:59 p.m. |
| PD | Predicate disambiguation | batch_69e6be9a65888190a66598d62d20366c |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:07 p.m.