Triple
T22428266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holmes & Watson |
E554428
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Mosaic |
—
|
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: Mosaic | Statement: [Holmes & Watson, productionCompany, Mosaic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mosaic Context triple: [Holmes & Watson, productionCompany, Mosaic]
-
A.
Mosaic
Mosaic is the highest elite status tier in the TrueBlue loyalty program, offering members enhanced travel benefits and premium perks.
-
B.
Mosaic
chosen
Mosaic is a 2017 experimental murder-mystery project by Steven Soderbergh that was released both as an interactive storytelling app and as a traditional HBO miniseries.
-
C.
Mosaic
Mosaic is a pioneering early web browser that popularized the World Wide Web by introducing a user-friendly graphical interface for browsing internet content.
-
D.
Mosaic
Mosaic is a visual composition technique that assembles many small, often colorful elements into a larger cohesive image or pattern.
-
E.
Mosaique
"Mosaique" is a popular studio album by the Gipsy Kings that showcases their signature blend of flamenco, pop, and Latin rhythms.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e4f2d0c819091aa3558ea2ee630 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15a2f054c819093fbe173c8a4a544 |
completed | April 29, 2026, 1:09 a.m. |
Created at: April 16, 2026, 8:47 p.m.