Triple
T38405846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mama Fratelli |
E901325
|
entity |
| Predicate | relatedWorkStoryBy |
P204641
|
FINISHED |
| Object | Steven Spielberg |
E11668
|
NE 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: Steven Spielberg | Statement: [Mama Fratelli, relatedWorkStoryBy, Steven Spielberg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedWorkStoryBy Context triple: [Mama Fratelli, relatedWorkStoryBy, Steven Spielberg]
-
A.
relatedWorkByAttribution
Indicates that one work is connected to another through explicit attribution, such as citation, acknowledgment, or credit given by the creator or source.
-
B.
relatedWorkByKey
Indicates a relationship where one work is linked or associated to another work identified by a specific key or identifier.
-
C.
relatedWorkForm
Indicates a relationship in which one work is connected to another through a different form or version (e.g., adaptation, translation, or other format variation).
-
D.
associatedWork
Indicates that there exists a related or connected work (such as a publication, creative piece, or project) that is meaningfully linked to the subject.
-
E.
relatedWorkBySubject
Indicates a relationship where one work is connected to another through sharing the same subject or topic.
- F. None of above. chosen
Provenance (5 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_69f76e61e79c81908b787d83b46ab92b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037cae084081909004d77514c5f286 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41b2bd3c9c819091325c6f49ab9f0b |
completed | June 28, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_6a037a1c850c819088795a7ae59bdeb8 |
completed | May 12, 2026, 7:06 p.m. |
| PDg | Predicate description generation | batch_6a037c84ecbc81908232e5215355f43b |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:31 p.m.