Triple
T11974208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mathews balancing test |
E284996
|
entity |
| Predicate | firstFactor |
P102585
|
FINISHED |
| Object | private interest affected by the official action |
—
|
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: private interest affected by the official action | Statement: [Mathews balancing test, firstFactor, private interest affected by the official action]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstFactor Context triple: [Mathews balancing test, firstFactor, private interest affected by the official action]
-
A.
first
Indicates that one entity precedes all others in an ordered sequence or ranking.
-
B.
firstTerms
Indicates that the related entities are the initial elements or starting terms in a sequence, series, or ordered collection.
-
C.
firstWord
Indicates that one entity is the first word in the sequence or text associated with another entity.
-
D.
firstSeries
Indicates that one entity is the initial or earliest series in an ordered sequence of related series.
-
E.
firstLeg
Indicates that one entity represents the initial segment or starting portion of a multi-part journey, sequence, or process involving another entity.
- 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_69d6ab2eaeb881909f7914758f859413 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9039107e48190ae4c4efd6257dd3c |
completed | April 10, 2026, 2:05 p.m. |
| PD | Predicate disambiguation | batch_69d8bb40f30c8190a0e0719bd67542bf |
completed | April 10, 2026, 8:56 a.m. |
| PDg | Predicate description generation | batch_69d8dd0ba0f88190b7d5e358c27ca184 |
completed | April 10, 2026, 11:20 a.m. |
Created at: April 8, 2026, 9:46 p.m.