Triple
T32012090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miss Martian’s human form (M'gann M'orzz) on Supergirl |
E817432
|
entity |
| Predicate | sharesBackstoryElementWith |
P3438
|
FINISHED |
| Object | J'onn J'onzz as Martian genocide survivor |
—
|
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: J'onn J'onzz as Martian genocide survivor | Statement: [Miss Martian’s human form (M'gann M'orzz) on Supergirl, sharesBackstoryElementWith, J'onn J'onzz as Martian genocide survivor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesBackstoryElementWith Context triple: [Miss Martian’s human form (M'gann M'orzz) on Supergirl, sharesBackstoryElementWith, J'onn J'onzz as Martian genocide survivor]
-
A.
sharesStoryElementsWith
Indicates that two narratives or works have overlapping or similar plot points, themes, characters, or other storytelling components.
-
B.
sharesHistoryWith
chosen
Indicates that two entities have a common or overlapping past, such as shared experiences, events, or origins.
-
C.
sharesWith
Indicates that one entity gives another entity access to or use of something it possesses.
-
D.
sharesItem
Indicates that one entity provides access to or distributes an item to another entity.
-
E.
sharesTimelineWith
Indicates that two entities participate in or are associated with the same timeline, sequence of events, or temporal context.
- 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_69f348f9e5d081908cc3f57c4942af52 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff3b32ee148190a3ba3b7600943fef |
completed | May 9, 2026, 1:48 p.m. |
| PD | Predicate disambiguation | batch_69ff3a238af88190a2c2245e30299e48 |
completed | May 9, 2026, 1:44 p.m. |
Created at: May 1, 2026, 12:15 a.m.