Triple
T28367873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earls Colne |
E718538
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object |
White Colne
White Colne is a small rural village in Essex, England, situated near the River Colne and surrounded by countryside.
|
E1813879
|
NE 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: White Colne | Statement: [Earls Colne, nearbySettlement, White Colne]
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: White Colne Triple: [Earls Colne, nearbySettlement, White Colne]
Generated description
White Colne is a small rural village in Essex, England, situated near the River Colne and surrounded by countryside.
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_69eff6ed5af48190be4e0adf298223e0 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64c5759ec8190befb634523ac87e2 |
completed | May 2, 2026, 7:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1627d42bec819087df30f3cca1d283 |
completed | May 26, 2026, 11:08 p.m. |
| NEDg | Description generation | batch_6a1628f366d88190b10dda8b0ab63762 |
completed | May 26, 2026, 11:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a16297370d08190a0088aa14476bb1f |
completed | May 26, 2026, 11:14 p.m. |
Created at: April 28, 2026, 12:56 a.m.