Triple
T12958570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winterfell |
E310078
|
entity |
| Predicate | hasCryptsFor |
P5511
|
FINISHED |
| Object | deceased members of House Stark |
—
|
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: deceased members of House Stark | Statement: [Winterfell, hasCryptsFor, deceased members of House Stark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCryptsFor Context triple: [Winterfell, hasCryptsFor, deceased members of House Stark]
-
A.
hasCrypt
chosen
Indicates that one entity possesses, contains, or is associated with a crypt belonging to or located within it.
-
B.
hasCrack
Indicates that one entity possesses or exhibits a crack, fracture, or split in its structure or surface.
-
C.
hasCreature
Indicates that one entity possesses, contains, or is associated with a particular creature.
-
D.
hasMystery
Indicates that one entity possesses, contains, or is associated with something unknown, secret, or unexplained in relation to another entity.
-
E.
hasCP
Indicates that an entity possesses, is associated with, or is characterized by a specific CP (such as a control point, contact person, or configuration parameter), depending on the domain context.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97dba57988190b786ffed55687a72 |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:44 p.m.