Triple
T27005364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aum Shinrikyo |
E680225
|
entity |
| Predicate | notableVictimCount |
P63692
|
FINISHED |
| Object | 13 killed in Tokyo subway sarin attack |
—
|
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: 13 killed in Tokyo subway sarin attack | Statement: [Aum Shinrikyo, notableVictimCount, 13 killed in Tokyo subway sarin attack]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableVictimCount Context triple: [Aum Shinrikyo, notableVictimCount, 13 killed in Tokyo subway sarin attack]
-
A.
notableVictim
Indicates that the subject is a person or entity who is notably recognized as a victim of the object (such as an event, crime, or harmful action).
-
B.
notableVictims
Indicates that the object is a person or group who is especially well-known or significant as a victim of the subject.
-
C.
numberOfVictimsClaimed
Indicates the reported count of victims associated with a particular event, incident, or action.
-
D.
numberOfVictimsKilled
chosen
Indicates the count of victims who were killed as a result of the referenced event or action.
-
E.
numberOfVictimsConfirmed
Indicates the confirmed count of victims associated with an event, incident, or situation.
- 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_69eeeb53939c8190bd431f32b060f01f |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69ff65987ff88190b09be64f7c0e1da9 |
completed | May 9, 2026, 4:49 p.m. |
| PD | Predicate disambiguation | batch_69ff6525b0548190bef7a9f009e00bb8 |
completed | May 9, 2026, 4:47 p.m. |
Created at: April 27, 2026, 7 a.m.