Triple
T11871950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eternals (Marvel Comics) |
E282425
|
entity |
| Predicate | teamMember |
P7184
|
FINISHED |
| Object | Makkari |
E830876
|
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: Makkari | Statement: [Eternals (Marvel Comics), teamMember, Makkari]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Makkari Context triple: [Eternals (Marvel Comics), teamMember, Makkari]
-
A.
Makkari
chosen
Makkari is a super-speed-powered Eternal and one of the central immortal heroes featured in the Marvel Cinematic Universe film "Eternals."
-
B.
Mesharu
Mesharu is a minor Mesopotamian deity associated with justice and righteousness, traditionally regarded as a child of the sun god Shamash.
-
C.
Maki Ziro
Maki Ziro is a Japanese physicist known as a prominent student and collaborator of theoretical physicist Shoichi Sakata.
-
D.
Mamoru
Mamoru is a Japanese masculine given name commonly borne by notable figures in politics, arts, and entertainment.
-
E.
Mako Kamitsuna
Mako Kamitsuna is a Japanese-born film editor and filmmaker known for her work on critically acclaimed independent films, including the period drama "Mudbound."
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903024afc8190a97aa3263dc7d017 |
completed | April 10, 2026, 2:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281bcd4f88190bb2103a165cb9578 |
completed | April 29, 2026, 10:10 p.m. |
Created at: April 8, 2026, 9:43 p.m.