Triple
T18283067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heaven Sent |
E437910
|
entity |
| Predicate | arcRole |
P129297
|
FINISHED |
| Object | penultimate episode of Series 9 |
—
|
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: penultimate episode of Series 9 | Statement: [Heaven Sent, arcRole, penultimate episode of Series 9]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: arcRole Context triple: [Heaven Sent, arcRole, penultimate episode of Series 9]
-
A.
anchorRole
Indicates that one entity serves as a primary or reference role to which other related roles or elements are connected or aligned.
-
B.
notableArcRole
chosen
Indicates that one entity holds a particularly important or prominent role within a narrative arc or storyline in relation to another entity.
-
C.
antRole
Indicates that one entity has a specific role, function, or responsibility in relation to another entity.
-
D.
actorRole
Indicates that an entity participates in an event or action in a specific capacity or function (such as performer, initiator, or responsible party).
-
E.
gammaRole
Indicates a tertiary or supporting role that an entity plays within a structured hierarchy of roles or participants in an event or relationship.
- 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50057c5c881909fcda72f4a98c8c3 |
completed | April 19, 2026, 4:18 p.m. |
| PD | Predicate disambiguation | batch_69e44fd81c788190b08c6be3b07a08c5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:35 a.m.