Triple
T33825657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sea of Death |
E866947
|
entity |
| Predicate | hasMainCharactersType |
P203241
|
FINISHED |
| Object | marginalized workers |
—
|
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: marginalized workers | Statement: [Sea of Death, hasMainCharactersType, marginalized workers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainCharactersType Context triple: [Sea of Death, hasMainCharactersType, marginalized workers]
-
A.
hasMainCharacterFrom
Indicates that a work of fiction has a main character who originates from or belongs to a specified place, group, or source.
-
B.
hasMainThemeCharacter
Indicates that a work (such as a story, film, or game) features a specific character as its central or primary thematic focus.
-
C.
mainCharactersAre
Indicates that the specified entities serve as the primary or central characters in a narrative or work.
-
D.
hasNumberOfPrincipalCharacters
Indicates the relationship that specifies how many main or principal characters are associated with a given entity.
-
E.
hasMainTitleCharacter
Indicates that a work’s primary or main title is centered on, derived from, or explicitly names a particular character.
- F. None of above. chosen
Provenance (4 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_69f34991dd248190a659541588506b3c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a01416f8a8c8190abc12f68bd23dcc3 |
completed | May 11, 2026, 2:39 a.m. |
| PD | Predicate disambiguation | batch_6a013f3bc2e48190a51ec2707bbdd474 |
completed | May 11, 2026, 2:30 a.m. |
| PDg | Predicate description generation | batch_6a01416eb9588190ad74541d0640a4ba |
completed | May 11, 2026, 2:39 a.m. |
Created at: May 1, 2026, 1:46 a.m.