Triple
T1633995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CapitalG |
E35322
|
entity |
| Predicate | focusesOnStage |
P31
|
FINISHED |
| Object | later-stage companies |
—
|
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: later-stage companies | Statement: [CapitalG, focusesOnStage, later-stage companies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusesOnStage Context triple: [CapitalG, focusesOnStage, later-stage companies]
-
A.
focusesOn
chosen
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
B.
isMainStageOf
Indicates that one entity serves as the primary or central stage or platform on which the other entity occurs, is presented, or is featured.
-
C.
focusesOnTeam
Indicates that the subject directs attention, effort, or priority toward a particular team as the main area of concern or activity.
-
D.
followsStage
Indicates that one stage occurs after and in sequence with another stage in a process or workflow.
-
E.
stage
Indicates that an entity organizes, presents, or performs another entity (such as an event, show, or action) as a staged occurrence.
- 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_69a886036bc081909ff5de16dbe5e8ea |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a96083e7308190abbf025fe8e43abb |
completed | March 5, 2026, 10:52 a.m. |
| PD | Predicate disambiguation | batch_69a907cac610819083cafd4396b6d66c |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.