Triple
T19880367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Tierney Clark |
E477752
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Clark |
—
|
NE NERFINISHED |
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: Clark | Statement: [William Tierney Clark, familyName, Clark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clark Context triple: [William Tierney Clark, familyName, Clark]
-
A.
Clark
Clark is the middle name of Herbert Hoover, the 31st president of the United States.
-
B.
Clark
chosen
Clark is a masculine given name of English origin commonly used in the United States and other English-speaking countries.
-
C.
Clark
Clark is a major aviation and economic hub in the Philippines, centered around Clark International Airport and the surrounding Clark Freeport and Special Economic Zone in Pampanga.
-
D.
Clark
Clark is a character from John Carpenter's horror film "The Thing," known as the dog handler at the Antarctic research station.
-
E.
Clark
Clark is an electoral division in the Tasmanian House of Assembly that encompasses parts of the greater Hobart area.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658de4b288190a41bee67f570be1e |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:52 p.m.