Triple
T26352233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ikon Park |
E662931
|
entity |
| Predicate | historicalHomeGroundOf |
P129928
|
FINISHED |
| Object | Carlton Football Club |
—
|
NE NERFINISHED |
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: Carlton Football Club | Statement: [Ikon Park, historicalHomeGroundOf, Carlton Football Club]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalHomeGroundOf Context triple: [Ikon Park, historicalHomeGroundOf, Carlton Football Club]
-
A.
homeGroundNameHistory
Indicates the historical sequence of names that have been used for an entity’s home ground or home venue over time.
-
B.
previousHomeGroundLocatedIn
Indicates that the location specified is where an entity’s former or earlier home ground was situated.
-
C.
historicHomeGround
chosen
Indicates that a location has traditionally served as the primary or long-standing home venue for a team, organization, or group.
-
D.
homeFieldSince
Indicates that a particular location has served as the designated home field or home venue for an entity starting from a specified point in time.
-
E.
primaryHomeGroundNot
Indicates that the specified location is explicitly not the entity’s primary home ground.
- 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_69ee8130fc44819094e5ab1da201cd7b |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
Created at: April 26, 2026, 10:46 p.m.