Triple
T36776657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Return of the Shadow |
E908640
|
entity |
| Predicate | mainCharacterInDrafts |
P167070
|
FINISHED |
| Object | Bilbo Baggins |
—
|
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: Bilbo Baggins | Statement: [The Return of the Shadow, mainCharacterInDrafts, Bilbo Baggins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainCharacterInDrafts Context triple: [The Return of the Shadow, mainCharacterInDrafts, Bilbo Baggins]
-
A.
mainCharacterWorksHere
Indicates that the primary or central character is employed at or performs their work in the referenced place or organization.
-
B.
mainCharacterField
chosen
Indicates that one entity is designated as the primary or central character associated with another entity, such as a work or narrative.
-
C.
currentCharacter
Indicates that an entity is the character presently in focus or being actively considered in a given context or sequence.
-
D.
mainCharacterCommunity
Indicates that a community is the primary social or group context associated with the main character in a narrative or work.
-
E.
mainMortalCharacter
Indicates that the referenced entity serves as the primary mortal (non-immortal) character in the context of a story or narrative.
- 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_69f76e798aa08190ace31098d1b13e9f |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd6f9d600c8190acf495b7fc632e4b |
completed | May 8, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69fd6e98a2948190a9f78c415ad23b8c |
completed | May 8, 2026, 5:03 a.m. |
Created at: May 3, 2026, 4:12 p.m.