Triple
T8666444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Critias |
E205684
|
entity |
| Predicate | conflictOfDeath |
P83970
|
FINISHED |
| Object | conflict between democrats and oligarchs in Athens |
—
|
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: conflict between democrats and oligarchs in Athens | Statement: [Critias, conflictOfDeath, conflict between democrats and oligarchs in Athens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conflictOfDeath Context triple: [Critias, conflictOfDeath, conflict between democrats and oligarchs in Athens]
-
A.
diedInConflict
Indicates that an entity lost their life as a direct result of a specific conflict or war.
-
B.
deathToll
Indicates the number of deaths resulting from a particular event, situation, or cause.
-
C.
hasBurialsFromConflict
Indicates that the subject location or site contains burials that originated as a result of a specific conflict or violent event.
-
D.
militaryConflict
Indicates a relationship where two or more parties are engaged in organized, armed hostilities or warfare against each other.
-
E.
nativeCasualties
Indicates that native or indigenous people suffered deaths or injuries as a result of a particular event, action, or conflict.
- 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_69ca83516ae88190aefe034b3bc589e3 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc48a1dd1481908c56abca48fcd562 |
completed | March 31, 2026, 10:20 p.m. |
| PD | Predicate disambiguation | batch_69cc4564e018819081036722f3e42a71 |
completed | March 31, 2026, 10:06 p.m. |
| PDg | Predicate description generation | batch_69cc46c330bc8190a9b644078881c6ff |
completed | March 31, 2026, 10:12 p.m. |
Created at: March 30, 2026, 6:31 p.m.