Triple
T19486231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cio-Cio San |
E487517
|
entity |
| Predicate | killsHerselfAfter |
P118269
|
FINISHED |
| Object | learning of Pinkerton’s American wife |
—
|
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: learning of Pinkerton’s American wife | Statement: [Cio-Cio San, killsHerselfAfter, learning of Pinkerton’s American wife]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: killsHerselfAfter Context triple: [Cio-Cio San, killsHerselfAfter, learning of Pinkerton’s American wife]
-
A.
defendsHerselfBy
Indicates that a female entity protects or justifies herself using a specified method, action, or means.
-
B.
killedHimselfAfter
chosen
Indicates that an individual committed suicide following a specified event or time.
-
C.
killsByProxy
Indicates that one entity causes the death of another entity indirectly through an intermediary or agent rather than committing the act personally.
-
D.
canKill
Indicates that one entity has the ability or potential to cause the death of another entity.
-
E.
killMechanism
Indicates the method or process by which one entity causes the death or destruction of another.
- 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6343f46e88190b7ba65c210285bee |
completed | April 20, 2026, 2:12 p.m. |
| PD | Predicate disambiguation | batch_69e4fd7883308190b73912a71a35a835 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:39 p.m.