Triple
T8759278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Schaefer |
E208152
|
entity |
| Predicate | workOn |
P30363
|
FINISHED |
| Object | Swarm |
E755589
|
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: Swarm | Statement: [Michael Schaefer, workOn, Swarm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Swarm Context triple: [Michael Schaefer, workOn, Swarm]
-
A.
Swarm
Swarm is a giant wasp-like Skylander character from the Skylanders: Giants video game, known for his flying abilities and stinger-based combat.
-
B.
Swarm
Swarm is a creative work—likely a film, series, or literary piece—recognized as a significant contribution by Fam Udeorji.
-
C.
Swarm
chosen
Swarm is a work created by Michael Schaefer, recognized as one of his notable artistic or creative projects.
-
D.
The Swarm
"The Swarm" is a poem by Winter Trees, likely exploring themes of collective movement, nature, or transformation through vivid, atmospheric imagery.
-
E.
The Swarm
The Swarm is a winged steel roller coaster at Thorpe Park in the UK, themed around a post-apocalyptic disaster with near-miss elements and inversions.
- 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_69ca835cd6b08190bd7c63db92f53c86 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5df81c58819089af99306e103dbb |
completed | March 31, 2026, 11:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf6f10aea48190bb63a4b2fdd72338 |
completed | April 3, 2026, 7:41 a.m. |
Created at: March 30, 2026, 6:40 p.m.