Triple
T31679848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hemel Hempstead Town F.C. |
E808506
|
entity |
| Predicate | homeStadiumAddressLocality |
P136724
|
FINISHED |
| Object |
Vauxhall Road, Hemel Hempstead
Vauxhall Road, Hemel Hempstead is a football ground in Hemel Hempstead, England, best known as the home venue of Hemel Hempstead Town F.C.
|
E1973239
|
NE FINISHED |
How this triple was built (3 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: Vauxhall Road, Hemel Hempstead | Statement: [Hemel Hempstead Town F.C., homeStadiumAddressLocality, Vauxhall Road, Hemel Hempstead]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Vauxhall Road, Hemel Hempstead Triple: [Hemel Hempstead Town F.C., homeStadiumAddressLocality, Vauxhall Road, Hemel Hempstead]
Generated description
Vauxhall Road, Hemel Hempstead is a football ground in Hemel Hempstead, England, best known as the home venue of Hemel Hempstead Town F.C.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeStadiumAddressLocality Context triple: [Hemel Hempstead Town F.C., homeStadiumAddressLocality, Vauxhall Road, Hemel Hempstead]
-
A.
homeStadiumCityDistrict
Indicates the city district in which an entity’s home stadium is located.
-
B.
homeStadiumLocatedIn
chosen
Indicates that the home stadium of a sports team or organization is geographically situated within a specified location or region.
-
C.
homeStadiumSituatedOn
Indicates that a team's home stadium is physically located on or within the grounds of a specified site or area.
-
D.
homeStadiumTeam
Indicates that a particular stadium serves as the designated home venue for a specific sports team.
-
E.
homeStadiumAlsoKnownAs
Indicates that an alternative or alias name is used for a stadium that serves as a team's home venue.
- F. None of above.
Provenance (6 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_69f348dcf5d48190ac25b1365ae717a8 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b84b8d55481908f187184f0886ab3 |
completed | June 12, 2026, 4:02 a.m. |
| NEDg | Description generation | batch_6a2b854efcc88190a0ad9b5f2aaecf26 |
completed | June 12, 2026, 4:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2b85ee4f088190a5b413a6b7d0e1b5 |
completed | June 12, 2026, 4:07 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:04 p.m.