Triple
T21742141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | compensation committee of Twitter, Inc. |
E536682
|
entity |
| Predicate | usedToExistAt |
P34268
|
FINISHED |
| Object | Twitter, Inc. as a publicly traded company |
—
|
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: Twitter, Inc. as a publicly traded company | Statement: [compensation committee of Twitter, Inc., usedToExistAt, Twitter, Inc. as a publicly traded company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedToExistAt Context triple: [compensation committee of Twitter, Inc., usedToExistAt, Twitter, Inc. as a publicly traded company]
-
A.
existedUntil
Indicates that an entity continued to exist up to, but not necessarily beyond, a specified time or event.
-
B.
existedAs
Indicates that one entity had the status, form, or identity of another entity during a certain time or context.
-
C.
existedUnder
chosen
Indicates that one entity existed within the authority, jurisdiction, or domain of another entity during a certain period.
-
D.
usedAt
Indicates that something is employed, applied, or utilized at a particular place, time, or context.
-
E.
existedAfter
Indicates that one entity came into existence only after another entity already existed.
- 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_69e0c46df5448190b4322127ffc4c690 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01a7322348190b2145fa922c480ed |
completed | April 28, 2026, 2:24 a.m. |
| PD | Predicate disambiguation | batch_69e6969c16fc8190b5126c169317d85d |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:49 p.m.