Triple
T34693383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyanna Stark |
E890958
|
entity |
| Predicate | lastRequestContent |
P61661
|
FINISHED |
| Object | protect Jon Snow |
—
|
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: protect Jon Snow | Statement: [Lyanna Stark, lastRequestContent, protect Jon Snow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastRequestContent Context triple: [Lyanna Stark, lastRequestContent, protect Jon Snow]
-
A.
lastRequest
Indicates that an entity is the most recent one to have made a particular request or initiated an interaction.
-
B.
requestContent
chosen
Indicates that one entity asks another entity to provide specific information, data, or material.
-
C.
lastRequestTo
Indicates that one entity is the most recent recipient of a request made by another entity.
-
D.
contentLengthCategory
Indicates how an item’s content is classified into a length-based category (e.g., short, medium, long) based on its size or duration.
-
E.
coreRequest
Indicates that one entity makes a primary or central request directed toward another entity.
- 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_69f349db7ab8819086808e833f472871 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f727bde8f88190ad746ca515134ca1 |
completed | May 3, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_69f72739c30c81908642eef3feb3afcf |
completed | May 3, 2026, 10:45 a.m. |
Created at: May 1, 2026, 2:05 a.m.