Triple
T3250283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Starks |
E68159
|
entity |
| Predicate | timePeriodWithinWork |
P44456
|
FINISHED |
| Object | early 20th century American South |
—
|
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: early 20th century American South | Statement: [Joe Starks, timePeriodWithinWork, early 20th century American South]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timePeriodWithinWork Context triple: [Joe Starks, timePeriodWithinWork, early 20th century American South]
-
A.
workPeriod
Indicates the span of time during which an entity is engaged in a particular work or employment activity.
-
B.
timePeriodWithin
Indicates that one time period is entirely contained within the bounds of another time period.
-
C.
workSettingPeriod
Indicates the time period during which a particular work setting or employment context is in effect.
-
D.
hasWorkPeriod
chosen
Indicates that an entity is associated with a specific span of time during which it performs or is engaged in some work or activity.
-
E.
usedInBusinessHours
Indicates that something is utilized or occurs during designated business operating hours.
- 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_69ad858e4c708190aa31d486cfee8a6a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf40f7908190a450c3136fccb020 |
completed | March 8, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69ada41837e48190933572165be0ca38 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.