Triple
T35118815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tysha |
E1014112
|
entity |
| Predicate | memoryHaunts |
P15512
|
FINISHED |
| Object | Tyrion Lannister |
—
|
NE NERFINISHED |
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: Tyrion Lannister | Statement: [Tysha, memoryHaunts, Tyrion Lannister]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memoryHaunts Context triple: [Tysha, memoryHaunts, Tyrion Lannister]
-
A.
haunts
chosen
Indicates that one entity persistently appears in, lingers around, or psychologically troubles another entity or place, often in a recurring or unsettling way.
-
B.
memoryAffects
Indicates that one entity’s memory or recollection has an influence or impact on another entity or process.
-
C.
retainsMemoriesOf
Indicates that one entity continues to hold or preserve memories about another entity or about events involving that entity.
-
D.
memory
Indicates that an entity retains, recalls, or is associated with stored information or past experiences.
-
E.
erasesMemoriesOf
Indicates that one entity causes the memories of another entity to be removed or wiped out.
- 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_69f76dd8b6948190aaa32b081816bd94 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78f63c8788190b253a18de5ca1312 |
completed | May 3, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_69f78e2d71248190b850c2802ec170c0 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:01 p.m.