Triple
T38502256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed Lin |
E919868
|
entity |
| Predicate | Jing-nan seriesSetting |
P124559
|
FINISHED |
| Object | Taipei, Taiwan |
—
|
NE NERFINISHED |
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: Taipei, Taiwan | Statement: [Ed Lin, Jing-nan seriesSetting, Taipei, Taiwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Jing-nan seriesSetting Context triple: [Ed Lin, Jing-nan seriesSetting, Taipei, Taiwan]
-
A.
basedInSeriesSetting
chosen
Indicates that something (such as a work, event, or element) is situated within or occurs in the primary setting established by a particular series.
-
B.
seriesOf
Indicates that one entity is a sequence or ordered set of related items, events, or parts that collectively form or belong to another entity.
-
C.
situatedInSeries
Indicates that one entity is located or positioned within a particular series, sequence, or ordered collection of related items.
-
D.
narrativeSeries
Indicates that one narrative work belongs to, or is part of, an ordered series of related narratives.
-
E.
literarySeries
Indicates that one work is part of, or belongs to, a larger literary series that connects multiple related works.
- 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_69f76e9ddd4481908f8c04439d848f9d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:31 p.m.