Triple
T24290738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Locke |
E605807
|
entity |
| Predicate | bodyPartSevered |
P90819
|
FINISHED |
| Object | Jaime Lannister’s right hand |
—
|
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: Jaime Lannister’s right hand | Statement: [Locke, bodyPartSevered, Jaime Lannister’s right hand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyPartSevered Context triple: [Locke, bodyPartSevered, Jaime Lannister’s right hand]
-
A.
bodyPartAttacked
Indicates that a specific body part of an entity is the target or focus of an attack.
-
B.
injuredBodyPart
Indicates that an entity has sustained an injury specifically affecting a particular body part.
-
C.
lostLimb
Indicates that an entity has had one or more of its limbs removed or rendered permanently absent, typically as a result of injury, surgery, or trauma.
-
D.
lostLimbTo
chosen
Indicates that one entity has had a limb removed, severed, or rendered nonfunctional as a direct result of another entity or cause.
-
E.
rupturedSegmentOf
Indicates that one entity is a segment that has undergone rupture and is part of, or derived from, 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_69e295480d0c8190846fc3c2e2da1d4c |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f29155e3cc8190808723d6b56dcfc0 |
completed | April 29, 2026, 11:16 p.m. |
| PD | Predicate disambiguation | batch_69f1c45c6ec081908401b69424428100 |
completed | April 29, 2026, 8:42 a.m. |
Created at: April 18, 2026, 12:08 a.m.