Triple
T18319381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cape Cross |
E438828
|
entity |
| Predicate | notableProgeny |
P50188
|
FINISHED |
| Object |
Behkabad
Behkabad was a successful British Thoroughbred racehorse and sire, best known for winning the 1946 St Leger Stakes.
|
E1317779
|
NE FINISHED |
How this triple was built (4 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: Behkabad | Statement: [Cape Cross, notableProgeny, Behkabad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Behkabad Context triple: [Cape Cross, notableProgeny, Behkabad]
-
A.
Bekabad
Bekabad is an industrial city in eastern Uzbekistan known for its steel production and location along the Syr Darya River.
-
B.
Chaghasarai
Chaghasarai is the former name of Asadabad, a city in western Iran that serves as the capital of Hamadan Province’s Asadabad County.
-
C.
Jalalaqsi
Jalalaqsi is a town in central Somalia that serves as a local administrative and commercial center within the Hirshabelle State.
-
D.
Khankendy
Khankendy is an alternative name for the city of Khankendi, also widely known as Stepanakert, the principal city of the Nagorno-Karabakh region.
-
E.
Dastakert
Dastakert is a small town in southern Armenia known for its mountainous setting and former mining industry.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Behkabad Triple: [Cape Cross, notableProgeny, Behkabad]
Generated description
Behkabad was a successful British Thoroughbred racehorse and sire, best known for winning the 1946 St Leger Stakes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Behkabad Target entity description: Behkabad was a successful British Thoroughbred racehorse and sire, best known for winning the 1946 St Leger Stakes.
-
A.
Bekabad
Bekabad is an industrial city in eastern Uzbekistan known for its steel production and location along the Syr Darya River.
-
B.
Chaghasarai
Chaghasarai is the former name of Asadabad, a city in western Iran that serves as the capital of Hamadan Province’s Asadabad County.
-
C.
Jalalaqsi
Jalalaqsi is a town in central Somalia that serves as a local administrative and commercial center within the Hirshabelle State.
-
D.
Khankendy
Khankendy is an alternative name for the city of Khankendi, also widely known as Stepanakert, the principal city of the Nagorno-Karabakh region.
-
E.
Dastakert
Dastakert is a small town in southern Armenia known for its mountainous setting and former mining industry.
- F. None of above. chosen
Provenance (5 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50aa4d3308190883714e1ef6a1d84 |
completed | April 19, 2026, 5:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03c4c6094881909add4e2fe99a1bba |
completed | May 13, 2026, 12:24 a.m. |
| NEDg | Description generation | batch_6a03c52d0ba48190845d461df02c3aa3 |
completed | May 13, 2026, 12:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03c5dd07488190ae04c6b406ab29c9 |
completed | May 13, 2026, 12:29 a.m. |
Created at: April 10, 2026, 10:36 a.m.