Triple
T31419133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Man-Thing |
E801481
|
entity |
| Predicate | projectInvolved |
P58621
|
FINISHED |
| Object | super-soldier serum variant |
—
|
LITERAL 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: super-soldier serum variant | Statement: [Man-Thing, projectInvolved, super-soldier serum variant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: projectInvolved Context triple: [Man-Thing, projectInvolved, super-soldier serum variant]
-
A.
projectsBetween
Indicates a relationship where something is projected or extends from one entity to another across an intervening space or set of entities.
-
B.
projectModel
Indicates a relationship where one entity serves as a model, template, or representation for a project or projected outcome involving another entity.
-
C.
projectsOn
Indicates that one entity casts, directs, or extends itself onto the surface, area, or domain of another entity.
-
D.
relatedToProject
chosen
Indicates that an entity has a connection or association with a specific project, without specifying the exact nature of that involvement.
-
E.
project
Indicates that an entity plans, organizes, or carries out a structured effort or initiative aimed at achieving a specific goal or outcome.
- 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_69f348c26f048190b4adadd71b4596c5 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 30, 2026, 8:46 p.m.