Triple
T17815784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Allison Mack |
E444834
|
entity |
| Predicate | numberOfSmallvilleEpisodes |
P45771
|
FINISHED |
| Object | over 200 |
—
|
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: over 200 | Statement: [Allison Mack, numberOfSmallvilleEpisodes, over 200]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfSmallvilleEpisodes Context triple: [Allison Mack, numberOfSmallvilleEpisodes, over 200]
-
A.
numberOfEpisodes
Indicates the total count of episodes associated with a given entity, such as a series or season.
-
B.
numberOfSeasons
Indicates the total count of seasons associated with a particular entity (such as a series, competition, or event).
-
C.
hasEpisodeCountInFirstSeries
Indicates that an entity has a specific number of episodes in its first series or season.
-
D.
notableEpisodeCount
chosen
Indicates the number of episodes in which the subject is notably featured or recognized.
-
E.
hasEpisodeCountPerSeries
Indicates a relationship where a series is associated with the number of episodes it contains.
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4887f7d048190b6d813b9f0fab3e7 |
completed | April 19, 2026, 7:47 a.m. |
| PD | Predicate disambiguation | batch_69e3d8de28688190844b65acf6af54e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:14 a.m.