Triple
T31718077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff VanderMeer |
E809499
|
entity |
| Predicate | notableSeriesFirstInstallment |
P207502
|
FINISHED |
| Object | Annihilation |
E247497
|
NE 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: Annihilation | Statement: [Jeff VanderMeer, notableSeriesFirstInstallment, Annihilation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableSeriesFirstInstallment Context triple: [Jeff VanderMeer, notableSeriesFirstInstallment, Annihilation]
-
A.
notableSeriesDebut
Indicates that an entity is recognized for making its first significant appearance or debut within a particular series.
-
B.
notableSeries
Indicates that an entity is a significant or well-known installment within a particular series or franchise.
-
C.
notableOriginalSeries
Indicates that an entity is recognized as a significant or distinguished original series associated with another entity (such as a platform, creator, or franchise).
-
D.
seriesDebut
Indicates the first appearance or initial release of a series in which the subject entity is introduced.
-
E.
seriesPremiereOf
Indicates that one creative work (typically an episode) is the first-ever installment that begins a television or similar serialized series.
- F. None of above. chosen
Provenance (5 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_69f348df4e048190a4a5a9932ada78d6 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2d9d450e508190aa6de6f06fb66edb |
completed | June 13, 2026, 6:11 p.m. |
| PD | Predicate disambiguation | batch_6a0379e7aa0c8190bdc9ee4d54fc821b |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c7ee0388190a29faeb5cdb0950a |
completed | May 12, 2026, 7:16 p.m. |
Created at: April 30, 2026, 11:17 p.m.