Triple
T1587325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Mexico |
E34095
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Clovis |
E50841
|
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: Clovis | Statement: [New Mexico, hasCity, Clovis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clovis Context triple: [New Mexico, hasCity, Clovis]
-
A.
Clovis
chosen
Clovis is a small city in eastern New Mexico known as a regional hub for agriculture, rail transport, and nearby Cannon Air Force Base.
-
B.
Clovis
Clovis is a city in Fresno County, California, known as a gateway to the Sierra Nevada and for its historic Old Town district.
-
C.
Hrodebert
Hrodebert is an ancient Germanic given name meaning "fame-bright" or "bright glory," from which later names like Robert and Roberto are derived.
-
D.
King of the Franks
King of the Franks was the medieval royal title held by the monarchs who ruled over the Frankish people and their territories in Western Europe, particularly in what later became the Kingdom of France.
-
E.
Tacenwit
Tacenwit is an alternative name for the Shenwa language, a Zenati Berber language spoken in northern Algeria.
- 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_69a885fceb2c8190b47e0f7c0aefbff0 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9090b3a20819098fdb5605ee739d7 |
completed | March 5, 2026, 4:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad469b36548190b2bdf2324fbea30f |
completed | March 8, 2026, 9:51 a.m. |
Created at: March 4, 2026, 7:27 p.m.