Triple
T36481202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joan Watson |
E898819
|
entity |
| Predicate | seriesRunContext |
P92433
|
FINISHED |
| Object | Elementary (2012–2019) |
—
|
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: Elementary (2012–2019) | Statement: [Joan Watson, seriesRunContext, Elementary (2012–2019)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seriesRunContext Context triple: [Joan Watson, seriesRunContext, Elementary (2012–2019)]
-
A.
seriesRun
chosen
Indicates that one entity is a specific run, edition, or installment within an ongoing series associated with another entity.
-
B.
seriesRunStart
Indicates the point in time or event at which a particular series or sequence of related items begins.
-
C.
seriesContext
Indicates that one entity occurs within, belongs to, or is understood in relation to a broader series or sequence involving the other entity.
-
D.
seriesRunForRole
Indicates that a particular role is performed or held across multiple installments or episodes within a series.
-
E.
seriesRunEnd
Indicates the point or event at which a series, sequence, or recurring run of something concludes.
- 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_69f76e5a0e088190a2b6706aeb41723c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd64bc86848190a49f451a8fc5cf1e |
completed | May 8, 2026, 4:21 a.m. |
| PD | Predicate disambiguation | batch_69fd5ff4a648819090756d90fd195d9a |
completed | May 8, 2026, 4 a.m. |
Created at: May 3, 2026, 4:10 p.m.