Triple
T7291560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abergavenny Castle |
E164408
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Hamelin de Balun
Hamelin de Balun was an 11th-century Norman lord and marcher baron active in the Welsh borderlands.
|
E654274
|
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: Hamelin de Balun | Statement: [Abergavenny Castle, foundedBy, Hamelin de Balun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hamelin de Balun Context triple: [Abergavenny Castle, foundedBy, Hamelin de Balun]
-
A.
Douzy
Douzy is a small commune in the Ardennes department of northern France, known for its rural character and cross-border ties, including a town twinning with Kaiserslautern in Germany.
-
B.
Blondel
Blondel is a French surname historically associated with several notable figures in architecture, engineering, and the arts.
-
C.
Reynard
Reynard is a traditional European folkloric fox character, especially prominent in medieval tales as a clever trickster figure.
-
D.
Baron Grimm
Baron Grimm was a prominent 18th-century German-born man of letters and diplomat at the Russian court, best known for his influential literary and philosophical correspondence with European intellectuals and rulers.
-
E.
Willibald
Willibald is the given name of the influential 18th-century opera composer Christoph Willibald Gluck.
- 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: Hamelin de Balun Triple: [Abergavenny Castle, foundedBy, Hamelin de Balun]
Generated description
Hamelin de Balun was an 11th-century Norman lord and marcher baron active in the Welsh borderlands.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hamelin de Balun Target entity description: Hamelin de Balun was an 11th-century Norman lord and marcher baron active in the Welsh borderlands.
-
A.
Douzy
Douzy is a small commune in the Ardennes department of northern France, known for its rural character and cross-border ties, including a town twinning with Kaiserslautern in Germany.
-
B.
Blondel
Blondel is a French surname historically associated with several notable figures in architecture, engineering, and the arts.
-
C.
Reynard
Reynard is a traditional European folkloric fox character, especially prominent in medieval tales as a clever trickster figure.
-
D.
Baron Grimm
Baron Grimm was a prominent 18th-century German-born man of letters and diplomat at the Russian court, best known for his influential literary and philosophical correspondence with European intellectuals and rulers.
-
E.
Willibald
Willibald is the given name of the influential 18th-century opera composer Christoph Willibald Gluck.
- 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_69c6887a499881909dd23341399c59d8 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6eb6e8f3881908628b3d41aad70c6 |
completed | March 27, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7db4c04108190aeaa482e93482d02 |
completed | March 28, 2026, 1:44 p.m. |
| NEDg | Description generation | batch_69c7dc30bfd48190aa5d188471a3741d |
completed | March 28, 2026, 1:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7dc87994c81908e8f719741b8f3c8 |
completed | March 28, 2026, 1:49 p.m. |
Created at: March 27, 2026, 3 p.m.