Triple
T1658544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Tehran |
E35852
|
entity |
| Predicate | nationalRank |
P30985
|
FINISHED |
| Object | top-ranked university in Iran by many metrics |
—
|
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: top-ranked university in Iran by many metrics | Statement: [University of Tehran, nationalRank, top-ranked university in Iran by many metrics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nationalRank Context triple: [University of Tehran, nationalRank, top-ranked university in Iran by many metrics]
-
A.
countryRankContext
Indicates the relative position or ranking of a country within a specified contextual framework (such as economic, political, or performance-based criteria).
-
B.
frequencyRankInUnitedStates
Indicates the relative position of something in an ordered list based on how frequently it occurs within the United States.
-
C.
nationalOrder
Indicates that an entity has been awarded or holds a formal national honor, decoration, or order conferred by a country.
-
D.
stateRank
Indicates the relative position or standing of an entity within a specific state-level ordering or hierarchy.
-
E.
areaRankInUS
Indicates the relative position of an entity in a ranking of areas within the United States, based on its size.
- 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_69a88606aa808190aa0b421b4271f220 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf3359ce48190803b322db8ad6027 |
completed | March 6, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69a907cff53c8190b424f088478d3e2c |
completed | March 5, 2026, 4:34 a.m. |
| PDg | Predicate description generation | batch_69a99a4c3810819089d2dd0e23c8e46b |
completed | March 5, 2026, 2:59 p.m. |
Created at: March 4, 2026, 7:29 p.m.