Triple
T16842585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mae Martin |
E409448
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Taskmaster |
E257921
|
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: Taskmaster | Statement: [Mae Martin, appearedIn, Taskmaster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taskmaster Context triple: [Mae Martin, appearedIn, Taskmaster]
-
A.
Taskmaster
chosen
Taskmaster is a Marvel Comics supervillain and mercenary known for his photographic reflexes, which allow him to instantly mimic any physical skill he observes.
-
B.
The Task
The Task is a long reflective poem by William Cowper that blends meditative blank verse with vivid depictions of rural life and religious contemplation.
-
C.
Magic to Do
"Magic to Do" is the opening musical number from the Broadway show Pippin, known for its theatrical, vaudevillian style and its role in setting the tone for the production.
-
D.
Jobman
Jobman is a South African film directed by Darrell Roodt, known for its socially conscious storytelling within the country’s cinematic landscape.
-
E.
TaskManager
TaskManager is a core Apache Flink runtime component responsible for executing tasks, managing their resources, and handling data exchange between parallel processing units.
- 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_69d883952b048190887740a980b712ed |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b35167a48190b45a459023e3ab1b |
completed | April 18, 2026, 4:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c2a3296c8190978c1809264f66e1 |
completed | May 10, 2026, 5:38 p.m. |
Created at: April 10, 2026, 5:24 a.m.