Triple
T6331128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Allison Tolman |
E142382
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Mosaic (TV series) |
E374434
|
NE 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: Mosaic (TV series) | Statement: [Allison Tolman, notableWork, Mosaic (TV series)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mosaic (TV series) Context triple: [Allison Tolman, notableWork, Mosaic (TV series)]
-
A.
Mosaic (TV series)
chosen
Mosaic is a 2018 experimental murder-mystery television series created by Steven Soderbergh for HBO, notable for its interactive, branching narrative structure.
-
B.
Mosaic 1
Mosaic 1 is a lower-ranked or earlier version item within the Mosaic series, positioned beneath Mosaic 3 in the given hierarchy.
-
C.
Mosaic 2
Mosaic 2 is a mid-level elite status tier in JetBlue’s TrueBlue loyalty program, offering enhanced travel benefits and perks to frequent flyers.
-
D.
Mosaic 4
Mosaic 4 is a high-level elite status tier in TrueBlue’s loyalty program, offering enhanced benefits and perks to frequent travelers.
-
E.
Mosaic 3
Mosaic 3 is the highest elite status tier in TrueBlue, JetBlue Airways’ frequent flyer loyalty program, offering the most extensive set of premium travel benefits and perks.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c008d4d8e88190ad301c05b08722ac |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06514cbe8819096dbeb17ccb3e3d5 |
completed | March 22, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6041aac948190ad7dd4d5683903ed |
completed | March 27, 2026, 4:14 a.m. |
Created at: March 22, 2026, 4:30 p.m.