Triple
T27666503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2007 state of emergency in Pakistan |
E697240
|
entity |
| Predicate | announcedOnMedium |
P56263
|
FINISHED |
| Object | televised address |
—
|
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: televised address | Statement: [2007 state of emergency in Pakistan, announcedOnMedium, televised address]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: announcedOnMedium Context triple: [2007 state of emergency in Pakistan, announcedOnMedium, televised address]
-
A.
mentionedInMedium
Indicates that one entity is referenced, cited, or discussed within a particular medium (such as an article, video, or broadcast).
-
B.
announcedThrough
chosen
Indicates that an announcement or communication was made via a particular medium, channel, or intermediary.
-
C.
announcedAt
Indicates that an announcement or declaration was made at a specific time or event.
-
D.
announcedWith
Indicates that one entity was publicly revealed, declared, or introduced at the same time as, and in explicit association with, another entity.
-
E.
publiclyAnnouncedBy
Indicates that an action, decision, or piece of information was formally communicated to the public by a specified agent or entity.
- 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_69ef590b85a4819083ec7c12bd3c9c10 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f634a401e08190b2144d47f1df15e0 |
completed | May 2, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:38 p.m.