Triple
T20951324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somerton |
E515982
|
entity |
| Predicate | postcodeArea |
P920
|
FINISHED |
| Object | TA |
E469465
|
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: TA | Statement: [Somerton, postcodeArea, TA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TA Context triple: [Somerton, postcodeArea, TA]
-
A.
TA
TA is a common abbreviation for the Territorial Army, a volunteer reserve force that supports a country's regular armed forces.
-
B.
TA
TA is the standard abbreviation for *Transforming Anthropology*, a peer-reviewed academic journal focusing on critical and innovative scholarship in anthropology.
-
C.
TA
chosen
TA is the postcode area in southwest England that covers Taunton and surrounding towns including Minehead.
-
D.
TA
TA is a studio album by the American post-rock band Trans Am, showcasing their blend of experimental rock, electronic, and krautrock influences.
-
E.
TA
TA is a chain of full-service travel centers and truck stops across the United States, offering fuel, food, and amenities for professional drivers and motorists.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fade4e2c81908ab2619d74fcc5a7 |
completed | April 21, 2026, 4:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09278fef048190bccac96353f891fd |
completed | May 17, 2026, 2:27 a.m. |
Created at: April 16, 2026, 1:26 p.m.