Triple
T36187749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randyll Tarly |
E1046893
|
entity |
| Predicate | forcedSamwellTo |
P4672
|
FINISHED |
| Object | join the Night’s Watch |
—
|
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: join the Night’s Watch | Statement: [Randyll Tarly, forcedSamwellTo, join the Night’s Watch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forcedSamwellTo Context triple: [Randyll Tarly, forcedSamwellTo, join the Night’s Watch]
-
A.
forcedBy
chosen
Indicates that an entity is compelled or coerced into an action or state by another entity.
-
B.
forceType
Indicates the specific kind or category of force involved in an interaction or event (e.g., physical, legal, military, or other defined force classifications).
-
C.
forcedAbdication
Indicates that one entity compels another to give up a position of authority or leadership against their will.
-
D.
forceName
Indicates that a specific name or label is being imposed or enforced on an entity, overriding any existing or default naming.
-
E.
inForceWith
Indicates that a rule, condition, or agreement is currently active and being applied in conjunction with a specified entity or set of entities.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b69b333081909cadbed3fcb8ecf5 |
completed | May 3, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c2a5f8819094ad4621d7b97e0c |
completed | May 3, 2026, 8:49 p.m. |
Created at: May 3, 2026, 4:08 p.m.