Triple
T15378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Zuckerberg |
E306
|
entity |
| Predicate | announcedPledge |
P742
|
FINISHED |
| Object | to give away 99% of his Facebook shares over his lifetime |
—
|
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: to give away 99% of his Facebook shares over his lifetime | Statement: [Mark Zuckerberg, announcedPledge, to give away 99% of his Facebook shares over his lifetime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: announcedPledge Context triple: [Mark Zuckerberg, announcedPledge, to give away 99% of his Facebook shares over his lifetime]
-
A.
announcedAt
Indicates that an announcement or declaration was made at a specific time or event.
-
B.
announcementDate
Indicates the date on which an announcement is formally made or becomes publicly known.
-
C.
announcedInCity
Indicates that an announcement or declaration was formally made within a particular city.
-
D.
placeSigned
Indicates that an entity has signed or endorsed a document, agreement, or item at a particular place or location.
-
E.
donated
Indicates that one entity voluntarily gave something of value (such as money, goods, or time) to another entity, typically without expecting anything in return.
- F. None of above. chosen
Provenance (4 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_69a23d7ad88c8190bffe8ab091d86642 |
completed | Feb. 28, 2026, 12:57 a.m. |
| NER | Named-entity recognition | batch_69a240b249788190af8dbf7e80e9c91b |
completed | Feb. 28, 2026, 1:11 a.m. |
| PD | Predicate disambiguation | batch_69a23feae8c481908d8c50faac01fc5c |
completed | Feb. 28, 2026, 1:07 a.m. |
| PDg | Predicate description generation | batch_69a240b1551c81908abcae128ea45d00 |
completed | Feb. 28, 2026, 1:11 a.m. |
Created at: Feb. 28, 2026, 1:02 a.m.