Triple
T32591925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Augustus Waters |
E833093
|
entity |
| Predicate | hasBodyPartAmputated |
P53592
|
FINISHED |
| Object | leg |
—
|
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: leg | Statement: [Augustus Waters, hasBodyPartAmputated, leg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBodyPartAmputated Context triple: [Augustus Waters, hasBodyPartAmputated, leg]
-
A.
lostLimb
chosen
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.
-
B.
lostLimbTo
Indicates that one entity has had a limb removed, severed, or rendered nonfunctional as a direct result of another entity or cause.
-
C.
numberOfLegsLost
Indicates the number of legs an entity has lost as a result of some event or condition.
-
D.
targetAmputationLevel
Indicates the specific anatomical level or location on the body at which an amputation is or will be performed.
-
E.
lacksBodyPart
Indicates that one entity does not possess or is missing a specific body part in relation to another entity or a defined whole.
- 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_69f34929ff648190aded9424aa7564ae |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd4129a8848190a5002150278ac689 |
completed | May 8, 2026, 1:49 a.m. |
| PD | Predicate disambiguation | batch_69fd3e0515ec8190937c7af71ebc3875 |
completed | May 8, 2026, 1:36 a.m. |
Created at: May 1, 2026, 1:05 a.m.