Triple
T21592512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leviathan |
E532814
|
entity |
| Predicate | describedInJob41As |
P519
|
FINISHED |
| Object | fearsome creature |
—
|
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: fearsome creature | Statement: [Leviathan, describedInJob41As, fearsome creature]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: describedInJob41As Context triple: [Leviathan, describedInJob41As, fearsome creature]
-
A.
workDescribedIn
Indicates that a work (such as a publication or document) provides a description or account of the referenced entity.
-
B.
describedIn
chosen
Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
-
C.
workDescribes
Indicates that one work (such as a document, artwork, or dataset) provides a description or explanatory account of another work.
-
D.
workDescribedAs
Indicates that one entity’s work, project, or output is characterized, labeled, or referred to by a particular description, title, or phrase.
-
E.
usedInResumes
Indicates that something (such as a skill, phrase, or template) is employed or appears within one or more resumes.
- 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_69e0c46251648190876f0427cf2d321b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eefadeb56c8190bce79efadf3c644d |
completed | April 27, 2026, 5:57 a.m. |
| PD | Predicate disambiguation | batch_69e632109d048190b4ac3f14fe48d1a0 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:32 p.m.