Triple
T14510741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sifan Hassan |
E340387
|
entity |
| Predicate | WorldTitle |
P71562
|
FINISHED |
| Object | 2019 World champion in the 1500 metres |
—
|
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: 2019 World champion in the 1500 metres | Statement: [Sifan Hassan, WorldTitle, 2019 World champion in the 1500 metres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: WorldTitle Context triple: [Sifan Hassan, WorldTitle, 2019 World champion in the 1500 metres]
-
A.
worldTitleHeld
Indicates that an entity holds or has held a world-level title or championship in a particular domain or competition.
-
B.
worldTitles
chosen
Indicates that an entity has won one or more world championship titles in a given field or competition.
-
C.
internationalTitle
Indicates that an entity has a title or name used in international or cross-border contexts, distinct from its local or original title.
-
D.
UKTitle
Indicates that an entity holds a specific title or name as used in the United Kingdom context.
-
E.
worldTitleYear
Indicates that a work holds a world title associated with a specific year.
- 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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de94e5b7b48190878be271840c265b |
completed | April 14, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69de5c4ccba08190a988bfda0bc9f5cb |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:21 a.m.