Triple
T15315286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TD postcode area |
E366138
|
entity |
| Predicate | hasPostcodeDistrict |
P961
|
FINISHED |
| Object |
TD4
TD4 is a postcode district within the TD (Galashiels) postcode area in the Scottish Borders region of the United Kingdom.
|
E366138
|
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: TD4 | Statement: [TD postcode area, hasPostcodeDistrict, TD4]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TD4 Context triple: [TD postcode area, hasPostcodeDistrict, TD4]
-
A.
TD3
TD3 (Twin Delayed Deep Deterministic Policy Gradient) is an off-policy deep reinforcement learning algorithm that improves upon DDPG by reducing overestimation bias and stabilizing training for continuous control tasks.
-
B.
TD
TD is a UK postcode area covering parts of the Scottish Borders and northern England, including towns such as Galashiels and Berwick-upon-Tweed.
-
C.
TD
TD is the two-letter ISO 3166-1 alpha-2 country code assigned to Chad.
-
D.
TD
TD is the stock ticker symbol for The Toronto-Dominion Bank, one of Canada’s largest multinational banking and financial services institutions.
-
E.
D4
D4 is a commuter rail line within Moscow’s Moscow Central Diameters network, connecting suburban areas with the city through frequent, urban-style train service.
- 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: TD4 Triple: [TD postcode area, hasPostcodeDistrict, TD4]
Generated description
TD4 is a postcode district within the TD (Galashiels) postcode area in the Scottish Borders region of the United Kingdom.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: TD4 Target entity description: TD4 is a postcode district within the TD (Galashiels) postcode area in the Scottish Borders region of the United Kingdom.
-
A.
TD3
TD3 (Twin Delayed Deep Deterministic Policy Gradient) is an off-policy deep reinforcement learning algorithm that improves upon DDPG by reducing overestimation bias and stabilizing training for continuous control tasks.
-
B.
TD
chosen
TD is a UK postcode area covering parts of the Scottish Borders and northern England, including towns such as Galashiels and Berwick-upon-Tweed.
-
C.
TD
TD is the two-letter ISO 3166-1 alpha-2 country code assigned to Chad.
-
D.
TD
TD is the stock ticker symbol for The Toronto-Dominion Bank, one of Canada’s largest multinational banking and financial services institutions.
-
E.
D4
D4 is a commuter rail line within Moscow’s Moscow Central Diameters network, connecting suburban areas with the city through frequent, urban-style train service.
- F. None of above.
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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd050108190a584543cb93943a4 |
completed | April 16, 2026, 1:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fef8a688a48190848eb7f065aba146 |
completed | May 9, 2026, 9:04 a.m. |
| NEDg | Description generation | batch_69fef9cf76cc8190898ea1e648da18ed |
completed | May 9, 2026, 9:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fefab2d4cc8190acaa4b6341224633 |
completed | May 9, 2026, 9:13 a.m. |
Created at: April 10, 2026, 3:16 a.m.