Triple
T25159896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hope for Haiti Now telethon |
E626407
|
entity |
| Predicate | simulcastOn |
P18034
|
FINISHED |
| Object | internet |
—
|
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: internet | Statement: [Hope for Haiti Now telethon, simulcastOn, internet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: simulcastOn Context triple: [Hope for Haiti Now telethon, simulcastOn, internet]
-
A.
simulcastsOn
chosen
Indicates that a broadcast (such as a TV or radio program) is transmitted simultaneously on the specified channel, platform, or service.
-
B.
simulcastPartnerFrom
Indicates that one entity serves as the originating or source partner from which a simulcast (simultaneous broadcast or stream) is derived or distributed to another entity.
-
C.
broadcastLiveFrom
Indicates that an event or program is being transmitted in real time from a specific location or source.
-
D.
hasLiveBroadcast
Indicates that a live broadcast is currently being transmitted or available for the referenced entity.
-
E.
simulcastPartnerToYear
Indicates the year in which a simulcast partnership involving the subject entity took place.
- 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_69e2ff2834ec8190b0872e2ec3d76023 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f46d3f35848190b56a4373c97a7d64 |
completed | May 1, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 18, 2026, 6:31 a.m.