Triple
T14779990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandor Clegane |
E347365
|
entity |
| Predicate | traumaCause |
P14656
|
FINISHED |
| Object | childhood burning by Gregor Clegane |
—
|
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: childhood burning by Gregor Clegane | Statement: [Sandor Clegane, traumaCause, childhood burning by Gregor Clegane]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traumaCause Context triple: [Sandor Clegane, traumaCause, childhood burning by Gregor Clegane]
-
A.
causeOfInjury
chosen
Indicates that one entity is the source or reason that another entity sustained an injury.
-
B.
trauma
Indicates that an entity has experienced a deeply distressing or harmful event or series of events that cause lasting psychological or emotional impact.
-
C.
traumaTheme
Indicates that the relationship or context involves themes of trauma, such as psychological injury, distressing experiences, or their emotional and narrative impact.
-
D.
traumaLevel
Indicates the degree or severity of trauma experienced or present in relation to an entity or event.
-
E.
causeOf
Indicates that one entity brings about, produces, or is responsible for the occurrence or existence of another entity or event.
- 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_69d822e9b9e08190bedcc31a163fda82 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deca9c7cac8190ba900df95e42e318 |
completed | April 14, 2026, 11:15 p.m. |
| PD | Predicate disambiguation | batch_69de8c090d1081909b5a9bf437499d6c |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:31 a.m.