Triple
T3628352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | murder of Jean-Paul Marat |
E76893
|
entity |
| Predicate | hasPrecedingCondition |
P49638
|
FINISHED |
| Object | Marat’s skin disease |
—
|
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: Marat’s skin disease | Statement: [murder of Jean-Paul Marat, hasPrecedingCondition, Marat’s skin disease]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrecedingCondition Context triple: [murder of Jean-Paul Marat, hasPrecedingCondition, Marat’s skin disease]
-
A.
hasCondition
Indicates that an entity possesses, experiences, or is affected by a particular condition or state.
-
B.
hasPrecedence
Indicates that one entity occurs, is considered, or is applied before another in order, priority, or importance.
-
C.
hasPrecedingEvents
Indicates that one or more events occurred earlier in time or sequence relative to the referenced event.
-
D.
hasSubsequent
Indicates that one entity occurs, appears, or is positioned after another in a defined sequence or order.
-
E.
wasPrecededBy
Indicates that one event, state, or entity occurred or existed earlier in time than another.
- F. None of above. chosen
Provenance (4 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_69ad85dc03948190b35b7189e4175bcc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2df2b708190afef6925a53ec551 |
completed | March 8, 2026, 6:41 p.m. |
| PD | Predicate disambiguation | batch_69adb8410a5881909c94818d7060b2b0 |
completed | March 8, 2026, 5:56 p.m. |
| PDg | Predicate description generation | batch_69adb902e61c81908f10494f828e260f |
completed | March 8, 2026, 5:59 p.m. |
Created at: March 8, 2026, 3:23 p.m.