Triple
T15772653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reykjabók |
E382399
|
entity |
| Predicate | subjectMatterOfText |
P7040
|
FINISHED |
| Object | Icelandic family history |
—
|
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: Icelandic family history | Statement: [Reykjabók, subjectMatterOfText, Icelandic family history]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectMatterOfText Context triple: [Reykjabók, subjectMatterOfText, Icelandic family history]
-
A.
subjectMatter
Indicates the topic, theme, or content area that something (such as a work, document, or discussion) is about.
-
B.
subjectOfDescription
Indicates that the subject is the main entity being described or characterized in a given context or statement.
-
C.
subjectMatterScope
Indicates the thematic or topical domain that an action, statement, or resource pertains to or falls within.
-
D.
subjectType
Indicates the classification or category that defines what kind of entity the subject is.
-
E.
subjectOfWork
chosen
Indicates that one entity is the main topic, focus, or theme that a particular work (such as a book, article, or artwork) is about.
- 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e051976d248190adddd3db9f758e22 |
completed | April 16, 2026, 3:03 a.m. |
| PD | Predicate disambiguation | batch_69e00531e7ac8190a4190cce4f7fab4c |
completed | April 15, 2026, 9:37 p.m. |
Created at: April 10, 2026, 4:47 a.m.