Triple
T32951079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Allison DuBois |
E842952
|
entity |
| Predicate | networkOfOriginalRun |
P51134
|
FINISHED |
| Object | NBC |
—
|
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: NBC | Statement: [Allison DuBois, networkOfOriginalRun, NBC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: networkOfOriginalRun Context triple: [Allison DuBois, networkOfOriginalRun, NBC]
-
A.
originalNetworkRunStart
Indicates the time or event at which a network process, operation, or run was first initiated.
-
B.
originalNetwork
Indicates that one entity is the original or source network from which another network or derived entity is based or obtained.
-
C.
originalRunStartNetwork
chosen
Indicates the network on which a program or series first began its original broadcast run.
-
D.
showOriginalNetwork
Indicates that an entity reveals or specifies the original network or source network from which it originated or was first broadcast.
-
E.
originalRunEndNetwork
Indicates the network or system in which an original run, process, or sequence ultimately concludes or terminates.
- 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_69f3494a31f481909057136e49b4fe60 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f71f8ee0688190bd025f27993452d3 |
completed | May 3, 2026, 10:12 a.m. |
| PD | Predicate disambiguation | batch_69f71cc405c08190863565609a4c8499 |
completed | May 3, 2026, 10 a.m. |
Created at: May 1, 2026, 1:21 a.m.