Triple
T26955428
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harriet Hayes |
E678888
|
entity |
| Predicate | networkShowAirsOn |
P119906
|
FINISHED |
| Object | NBS (fictional network) |
—
|
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: NBS (fictional network) | Statement: [Harriet Hayes, networkShowAirsOn, NBS (fictional network)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: networkShowAirsOn Context triple: [Harriet Hayes, networkShowAirsOn, NBS (fictional network)]
-
A.
laterAppearsOnNetwork
Indicates that an entity is broadcast or becomes available on a specified network at a later time than some reference point or initial appearance.
-
B.
tvShareUS
Indicates the proportion of television viewership or audience share that occurs within the United States.
-
C.
televisionShow
Indicates that one entity is a television show associated with, or featured in relation to, another entity.
-
D.
airingNetworkOfSeries
chosen
Indicates the television network or channel on which a series is (or was) broadcast.
-
E.
laterAiredOnNetwork
Indicates that a program or episode was broadcast on a particular network at a later time than its original airing or than another specified airing.
- 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_69eeeb4e75f08190b14fc91ca4a91488 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f631850ae08190a0ba51e4f1e4ccb3 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 6:27 a.m.