Triple
T29081857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reality Stone |
E734002
|
entity |
| Predicate | originalBearerInMCU |
P97494
|
FINISHED |
| Object | Malekith the Accursed |
—
|
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: Malekith the Accursed | Statement: [Reality Stone, originalBearerInMCU, Malekith the Accursed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalBearerInMCU Context triple: [Reality Stone, originalBearerInMCU, Malekith the Accursed]
-
A.
firstBearer
chosen
Indicates that the subject is the earliest or original entity to hold, possess, or carry the specified role, title, attribute, or item.
-
B.
formerBearer
Indicates that an entity previously held or carried something (such as a title, role, or object) but no longer does so.
-
C.
eraOfBearer
Indicates that a time period or era is associated with, or characterizes, the bearer entity.
-
D.
bearerInstanceOf
Indicates that a bearer (such as an agent, object, or entity) is an instance or specific realization of a more general class, type, or role.
-
E.
bearerFounded
Indicates that the bearer (such as a person or organization) is the one who established or created the associated entity (such as a company, institution, or project).
- F. None of above.
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_69f05b0c0f28819086eae6e84f2ae472 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69ff49016dcc8190a8a43868c728b4f1 |
completed | May 9, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69ff4891924c8190b5be340e2520e012 |
completed | May 9, 2026, 2:45 p.m. |
Created at: April 28, 2026, 10:56 a.m.