Triple
T36145155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salvage |
E1045426
|
entity |
| Predicate | partOfTrilogyStructure |
P113808
|
FINISHED |
| Object | preceded by Voyage and Shipwreck |
—
|
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: preceded by Voyage and Shipwreck | Statement: [Salvage, partOfTrilogyStructure, preceded by Voyage and Shipwreck]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfTrilogyStructure Context triple: [Salvage, partOfTrilogyStructure, preceded by Voyage and Shipwreck]
-
A.
partOfTrilogy
Indicates that one work belongs to a set of three related works that together form a trilogy.
-
B.
hasPartInTrilogy
chosen
Indicates that an entity is one of the constituent parts (e.g., books, films, or episodes) that together form a specific trilogy.
-
C.
seriesNumberInTrilogy
Indicates the position or installment number that a work occupies within a specific trilogy.
-
D.
hasSequelInTrilogy
Indicates that one work in a trilogy is followed by another work that serves as its sequel within that same three-part series.
-
E.
trilogyDepicts
Indicates that a trilogy portrays, represents, or narratively focuses on a particular subject, event, or set of entities.
- 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_69f76e37ace88190a906b107d388f5d1 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00c59b03dc8190870f0dd24603a1ef |
completed | May 10, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_6a00c5178bc88190b2a0e03f38314035 |
completed | May 10, 2026, 5:49 p.m. |
Created at: May 3, 2026, 4:08 p.m.