Triple
T23297784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chief Martial Law Administrator of Pakistan |
E590219
|
entity |
| Predicate | Muhammad Zia-ul-HaqTermEnd |
P151756
|
FINISHED |
| Object | 1985-12-30 |
—
|
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: 1985-12-30 | Statement: [Chief Martial Law Administrator of Pakistan, Muhammad Zia-ul-HaqTermEnd, 1985-12-30]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Muhammad Zia-ul-HaqTermEnd Context triple: [Chief Martial Law Administrator of Pakistan, Muhammad Zia-ul-HaqTermEnd, 1985-12-30]
-
A.
successorAsTalibanLeader
Indicates that one individual became the next leader of the Taliban after another individual.
-
B.
officeEnd (Governor-General of Pakistan)
Indicates the date or point in time when the Governor-General of Pakistan’s term in office ended.
-
C.
governorOfPunjabAtTheTime
Indicates that one entity held the official position of Governor of Punjab during the time period relevant to the other entity or event.
-
D.
AfghanCommander
Indicates that an entity serves in the role of a military commander associated with Afghanistan.
-
E.
wasDirectorGeneralOf
Indicates that a person held the position of Director General of a specified organization or institution.
- 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_69e25d1c0ecc8190a355aa229f06d0e0 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196d083188190abaae77dd4cf2bae |
completed | April 29, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69effcf325f88190b320268c3c551abb |
completed | April 28, 2026, 12:18 a.m. |
| PDg | Predicate description generation | batch_69f01d88b4ec8190a2a17a88e0eda178 |
completed | April 28, 2026, 2:38 a.m. |
Created at: April 17, 2026, 5:03 p.m.