Triple
T23776912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Supreme Leader of the Islamic Emirate of Afghanistan |
E587699
|
entity |
| Predicate | has_title |
P144993
|
FINISHED |
| Object | Supreme Leader |
—
|
NE NERFINISHED |
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: Supreme Leader | Statement: [Supreme Leader of the Islamic Emirate of Afghanistan, has_title, Supreme Leader]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: has_title Context triple: [Supreme Leader of the Islamic Emirate of Afghanistan, has_title, Supreme Leader]
-
A.
hasTitleIn
Indicates that an entity holds or is associated with a specific title within a particular context, domain, or language.
-
B.
hasTitleOf
chosen
Indicates that one entity holds, bears, or is designated by the official title, name, or rank specified by another entity.
-
C.
containsTitle
Indicates that one entity includes or holds another entity’s title as part of its content or metadata.
-
D.
hadTitle
Indicates that an entity held or was assigned a specific title or formal designation.
-
E.
hasTitleFrom
Indicates that one entity holds or uses a title that originates from, or is conferred by, another 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_69e2490d245881909028226a1393d624 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1c46d55588190ad9c7e3c729b6b17 |
completed | April 29, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:16 p.m.