Triple
T37425435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tah-gah-jute |
E929974
|
entity |
| Predicate | soughtRevengeAfter |
P61789
|
FINISHED |
| Object | Yellow Creek massacre |
—
|
NE NERFINISHED |
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: Yellow Creek massacre | Statement: [Tah-gah-jute, soughtRevengeAfter, Yellow Creek massacre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: soughtRevengeAfter Context triple: [Tah-gah-jute, soughtRevengeAfter, Yellow Creek massacre]
-
A.
methodOfRevenge
Indicates a relationship where a specific action or strategy is used as the means by which revenge is carried out.
-
B.
causeOfVengeance
chosen
Indicates a relationship where one entity is the reason or trigger for another entity’s desire or act of vengeance.
-
C.
seeksJusticeAgainst
Indicates that one entity actively pursues legal or moral accountability or retribution directed at another entity.
-
D.
positionOnRevenge
Indicates a stance or attitude that one entity holds regarding the idea, acceptability, or pursuit of revenge.
-
E.
regretsKilling
Indicates that one entity feels remorse or regret about having killed another entity.
- 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_69f76ebf0f288190ba198a78341613b8 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:16 p.m.