Triple
T8048651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tehran Derby |
E187617
|
entity |
| Predicate | fanIncidents |
P80733
|
FINISHED |
| Object | occasionally associated with crowd trouble |
—
|
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: occasionally associated with crowd trouble | Statement: [Tehran Derby, fanIncidents, occasionally associated with crowd trouble]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fanIncidents Context triple: [Tehran Derby, fanIncidents, occasionally associated with crowd trouble]
-
A.
fanInvolved
Indicates that a fan actively participates in or is directly involved with a particular event, activity, or interaction.
-
B.
fanAccess
Indicates that an entity has permission or the ability to access fan-related content, features, or areas associated with another entity.
-
C.
fanAttendance
Indicates the number or presence of fans attending an event, such as a game, show, or performance.
-
D.
fanDestination
Indicates that one entity is the intended target or recipient of another entity’s enthusiasm, admiration, or fandom.
-
E.
fanBaseInteraction
Indicates interactions or engagements occurring between a fan base and the subject, such as communication, feedback, or participatory activities.
- 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_69ca82b15e948190a62fd7af5218426a |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3f7711f48190af2002533c2e426a |
completed | March 31, 2026, 3:28 a.m. |
| PD | Predicate disambiguation | batch_69cb049a1b9c8190811c396421ebf9c9 |
completed | March 30, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69cb14bcbbc0819094a98e7ffffb7a40 |
completed | March 31, 2026, 12:26 a.m. |
Created at: March 30, 2026, 5:24 p.m.