Triple
T8531617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Darvazeh Dowlat Metro Station |
E201963
|
entity |
| Predicate | hasAdjacentRole |
P83173
|
FINISHED |
| Object | access point to central Tehran |
—
|
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: access point to central Tehran | Statement: [Darvazeh Dowlat Metro Station, hasAdjacentRole, access point to central Tehran]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdjacentRole Context triple: [Darvazeh Dowlat Metro Station, hasAdjacentRole, access point to central Tehran]
-
A.
hasRelativeRole
Indicates that one entity holds a familial or kinship-based role in relation to another entity.
-
B.
hasAdjacentUse
Indicates that one entity is used or occurs directly next to another in space, time, or sequence.
-
C.
hasAuxiliaryRole
Indicates that an entity serves in a supporting or secondary capacity to another entity or primary role.
-
D.
isAdjacentTo
Indicates that one entity is directly next to or bordering another without anything of the same type in between.
-
E.
hasEquivalentRole
Indicates that two entities hold roles that are functionally the same or interchangeable in a given context.
- 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_69ca83228b24819085d22e7dc99f5d94 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe676e2ac8190b65a3d2a935776fd |
completed | March 31, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69cbd111bf988190be98c92a607c6456 |
completed | March 31, 2026, 1:50 p.m. |
| PDg | Predicate description generation | batch_69cbe30d453481908f897ed2b06e7534 |
completed | March 31, 2026, 3:06 p.m. |
Created at: March 30, 2026, 6:17 p.m.