Triple
T15036013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tegan Jovanka |
E378477
|
entity |
| Predicate | leftSeriesInYear |
P50786
|
FINISHED |
| Object | 1984 |
—
|
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: 1984 | Statement: [Tegan Jovanka, leftSeriesInYear, 1984]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leftSeriesInYear Context triple: [Tegan Jovanka, leftSeriesInYear, 1984]
-
A.
leftGroupYear
Indicates the year in which an entity departed from or ceased being a member of a particular group.
-
B.
leavesSeriesIn
chosen
Indicates that an entity departs from or exits a particular series, sequence, or collection it was previously part of.
-
C.
firstSeriesYear
Indicates the year in which a series (such as a TV show, book series, or sports league season) first began or was initially released.
-
D.
currentSeriesIntroduced
Indicates that an entity was first introduced or appeared in the currently ongoing series or installment of a work.
-
E.
seriesLeadAsOfEarly2020s
Indicates that the entity was the primary lead of the series during the early 2020s.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded82b29948190acda49cbec3f927a |
completed | April 15, 2026, 12:13 a.m. |
| PD | Predicate disambiguation | batch_69de9a67cbc481909c19c2de57de4eb7 |
completed | April 14, 2026, 7:50 p.m. |
Created at: April 10, 2026, 2:59 a.m.