Triple
T15700554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cullen house |
E380580
|
entity |
| Predicate | materialUsedInFiction |
P120354
|
FINISHED |
| Object | glass |
—
|
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: glass | Statement: [Cullen house, materialUsedInFiction, glass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialUsedInFiction Context triple: [Cullen house, materialUsedInFiction, glass]
-
A.
fictionalMaterial
Indicates that something is made of, composed of, or incorporates a material that exists only in fiction or imagination.
-
B.
fictionalMedium
Indicates that a work of fiction is presented or conveyed through a particular medium or format (such as a book, film, game, or comic).
-
C.
usedInFictionalWork
Indicates that something (such as a concept, object, or character) appears or is employed within a specific fictional work.
-
D.
hasFictionComponent
Indicates that something includes, contains, or is composed in part of a fictional element or work.
-
E.
basedOnInFiction
Indicates that a fictional work, character, or element is derived from, inspired by, or modeled after another real or fictional source.
- F. None of above. chosen
Provenance (4 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0b4d6b5788190883746ee82c799f5 |
completed | April 16, 2026, 10:07 a.m. |
| PD | Predicate disambiguation | batch_69e0051d639481909a10614e8f83e659 |
completed | April 15, 2026, 9:37 p.m. |
| PDg | Predicate description generation | batch_69e0b4d01c9c81909f6b611e8144c838 |
completed | April 16, 2026, 10:07 a.m. |
Created at: April 10, 2026, 4:45 a.m.