Triple
T3174795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Arrington |
E66435
|
entity |
| Predicate | hasCovered |
P29409
|
FINISHED |
| Object | Silicon Valley startups |
—
|
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: Silicon Valley startups | Statement: [Michael Arrington, hasCovered, Silicon Valley startups]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCovered Context triple: [Michael Arrington, hasCovered, Silicon Valley startups]
-
A.
hasCoveredEvent
chosen
Indicates that one entity has reported on, documented, or provided coverage of a particular event.
-
B.
hasCoverage
Indicates that one entity provides insurance or protection coverage for another entity or subject.
-
C.
hasCoveredLeague
Indicates that a person or organization has reported on, broadcast, or otherwise provided coverage of a particular sports league.
-
D.
isCoveredBy
Indicates that one entity is physically or conceptually overlaid, protected, or enclosed by another entity.
-
E.
hasCoverType
Indicates that one entity possesses or is associated with a specific type or category of cover.
- 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada670c800819098937783e2b05c7a |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e02677c8190a21d93b1259b2761 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.