Triple
T28202921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | My Hero |
E716934
|
entity |
| Predicate | mainCharacterHomePlanet |
P157933
|
FINISHED |
| Object | Ultron |
—
|
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: Ultron | Statement: [My Hero, mainCharacterHomePlanet, Ultron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainCharacterHomePlanet Context triple: [My Hero, mainCharacterHomePlanet, Ultron]
-
A.
homeworldType
Indicates the type or classification of a subject’s homeworld (e.g., planet, moon, habitat) in relation to that subject.
-
B.
residencePlanet
Indicates that an entity’s primary place of residence is located on a specified planet.
-
C.
homeworldLocation
Indicates the relationship between an entity and the specific place or celestial body that serves as its homeworld.
-
D.
adoptedHomeworld
Indicates that an entity has chosen or taken on a particular world as its primary place of residence or affiliation, distinct from its place of origin.
-
E.
protagonistHomeworld
chosen
Indicates the homeworld or place of origin associated with a story’s main protagonist.
- 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_69efd6b826908190857e6e7dad74ed93 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d26ceb08819091c71c001e954936 |
completed | May 3, 2026, 4:43 a.m. |
Created at: April 27, 2026, 10:33 p.m.