Triple
T14911028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tukey's biweight |
E371259
|
entity |
| Predicate | downweights |
P9925
|
FINISHED |
| Object | observations with large residuals |
—
|
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: observations with large residuals | Statement: [Tukey's biweight, downweights, observations with large residuals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: downweights Context triple: [Tukey's biweight, downweights, observations with large residuals]
-
A.
down
Indicates that one entity is located at a lower position or level relative to another entity or reference point.
-
B.
under
Indicates that one entity is positioned below or beneath another entity, often implying vertical alignment or coverage.
-
C.
isHeavilyWeightedToward
Indicates that something is strongly biased or disproportionately oriented in favor of one side, option, or aspect over others.
-
D.
reduces
chosen
Indicates that one entity causes a decrease in the amount, intensity, degree, or impact of another entity.
-
E.
demotes
Indicates that one entity reduces another entity’s rank, status, or level within a hierarchy or system.
- 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_69d85cc7ea3481908228b5acb7d06f12 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded61c6b9c8190a92934d49b98fe46 |
completed | April 15, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69de9a4a14a88190951bb8f4c60bd37b |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:26 a.m.