Triple
T6483700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter Harper |
E146456
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Harper |
E529622
|
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: Harper | Statement: [Walter Harper, familyName, Harper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harper Context triple: [Walter Harper, familyName, Harper]
-
A.
Harper
Harper is a small community located in Raleigh County, West Virginia, in the United States.
-
B.
Harper
Harper is a major American publishing house known for releasing a wide range of influential fiction and nonfiction works.
-
C.
Harper
Harper is a central character in the young adult novel "Watch Over Me," whose experiences and relationships drive much of the story’s emotional arc.
-
D.
Harper
chosen
Harper is a common English surname of Anglo-Saxon origin, historically referring to someone who played the harp.
-
E.
Lovejoy
Lovejoy is a British television drama series about a roguish yet charming antiques dealer with a knack for spotting valuable items and getting into trouble.
- 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_69c0090158c08190af0df9a2348d2d52 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c06a6de31c81909dd99d105f5bb4c2 |
completed | March 22, 2026, 10:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c653b24670819088fa8e0d7eb6f73b |
completed | March 27, 2026, 9:53 a.m. |
Created at: March 22, 2026, 4:52 p.m.