Triple
T15070598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poznań University of Technology |
E379864
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | PUT |
E379864
|
NE 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: PUT | Statement: [Poznań University of Technology, abbreviation, PUT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PUT Context triple: [Poznań University of Technology, abbreviation, PUT]
-
A.
PUT
chosen
PUT is the commonly used abbreviation for Poznań University of Technology, a leading technical university located in Poznań, Poland.
-
B.
PUT
PUT is the National Rail station code for Putney railway station in southwest London, England.
-
C.
Put
Put is a biblical nation or people, often identified with regions of North Africa, that appears among the allies of Gog in prophetic scriptures.
-
D.
UPD
UPD is the abbreviation for Upminster Depot, a London Underground maintenance and stabling facility serving the eastern end of the District line.
-
E.
UPD
UPD is the commonly used acronym for the University of the Philippines Diliman, the flagship campus of the national university of the Philippines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dff7f86df48190b3a2cf441fefb477 |
completed | April 15, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5cd4b6c8190aa9ff73d5be31864 |
completed | May 9, 2026, 3:11 a.m. |
Created at: April 10, 2026, 3:02 a.m.