Triple
T13148424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Effie Trinket |
E312398
|
entity |
| Predicate | bookAppearanceOrder |
P104268
|
FINISHED |
| Object | first book: The Hunger Games |
—
|
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: first book: The Hunger Games | Statement: [Effie Trinket, bookAppearanceOrder, first book: The Hunger Games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bookAppearanceOrder Context triple: [Effie Trinket, bookAppearanceOrder, first book: The Hunger Games]
-
A.
book4Covers
Indicates that one entity is the front or outer covering (such as a dust jacket or protective layer) of a book.
-
B.
displayOrder
Indicates the sequence or position in which items should be presented or shown relative to one another.
-
C.
appearsInBookNumber
chosen
Indicates that an entity is featured or mentioned in a specific book identified by its number within a series or collection.
-
D.
appearsOnTitlePageOf
Indicates that something is printed or shown on the title page of a document, book, or other published work.
-
E.
book2Covers
Indicates that one entity (typically a book) has another entity as its cover or is associated with a specific cover representation.
- 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_69d806aabde48190899e13e41659cae5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98cf054f88190b05ced98d5a22a62 |
completed | April 10, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69d98bbd1d088190b7c69f37fc6eeb64 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:11 p.m.