Triple
T4031031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fast Day (Massachusetts) |
E83709
|
entity |
| Predicate | dateReformEffect |
P5212
|
FINISHED |
| Object | introduction of Patriots’ Day |
—
|
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: introduction of Patriots’ Day | Statement: [Fast Day (Massachusetts), dateReformEffect, introduction of Patriots’ Day]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateReformEffect Context triple: [Fast Day (Massachusetts), dateReformEffect, introduction of Patriots’ Day]
-
A.
reformDate
chosen
Indicates the date on which a reform, change, or restructuring officially took effect or was implemented.
-
B.
dateChangesWith
Indicates that the date associated with one entity is altered or updated in conjunction with, or as a result of, a change involving another entity.
-
C.
dateRevisedTo
Indicates that an entity’s date has been updated or changed to a new specified date.
-
D.
reenvisionedDate
Indicates the date on which something was newly reimagined, redesigned, or conceptually revised.
-
E.
startDateChangedTo
Indicates that the start date of something has been modified from its previous value to a new specified date.
- 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_69aed92e29ac819080f7a98b594fec05 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb0dbb8481909ff2ee49dadcd1dc |
completed | March 9, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69aef8fe440c819093a7fa22c4ff3f1a |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:36 p.m.