Triple
T35037796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Psusennes I |
E1010975
|
entity |
| Predicate | bodyConditionAtDiscovery |
P129457
|
FINISHED |
| Object | badly decomposed |
—
|
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: badly decomposed | Statement: [Psusennes I, bodyConditionAtDiscovery, badly decomposed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyConditionAtDiscovery Context triple: [Psusennes I, bodyConditionAtDiscovery, badly decomposed]
-
A.
bodyPositionAtDiscovery
Indicates the physical position or posture in which a body was found at the time of its discovery.
-
B.
bodyDiscoveredIncorrupt
Indicates that a body was found in an unusually preserved or undecayed state, contrary to normal expectations of decomposition.
-
C.
clinicalCondition
chosen
Indicates that one entity has, exhibits, or is associated with a particular medical or health-related condition described by the other entity.
-
D.
discoveredOnBody
Indicates that something (such as an item, mark, or substance) was found on the surface or person of a body.
-
E.
discoveredOnBodyBy
Indicates that a body was discovered by a particular person or agent.
- 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_69f76dcea02c81908542a223f6d5059f |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7858cb6608190a0c2fa79c2d215a6 |
completed | May 3, 2026, 5:27 p.m. |
| PD | Predicate disambiguation | batch_69f7841812f081909d878955d114088e |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 3, 2026, 4:01 p.m.