Triple
T3077834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harrold |
E64179
|
entity |
| Predicate | hasRelatedName |
P3889
|
FINISHED |
| Object | Harroldson |
E64179
|
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: Harroldson | Statement: [Harrold, hasRelatedName, Harroldson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harroldson Context triple: [Harrold, hasRelatedName, Harroldson]
-
A.
Harrold
chosen
Harrold is a given name and surname, used as a variant spelling of Harold.
-
B.
Helleren
Helleren is a small historic settlement in Norway known for its traditional houses built under a large rock overhang near the Jøssingfjord.
-
C.
Hunte
The Hunte is a river in northwestern Germany that flows through Lower Saxony before joining the Weser.
-
D.
Howel
Howel is a given name and surname of Welsh origin, historically associated with several notable figures in Welsh history and literature.
-
E.
Hoyte
Hoyte is the first name of Hoyte van Hoytema, a renowned Dutch-Swedish cinematographer known for his work on major films such as "Interstellar" and "Dunkirk."
- 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_69ad857a8aec8190bfdfd9c14554ac5a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada1a6f6148190ae5cd6e45eda9006 |
completed | March 8, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1f88d32a08190b4e18da4b26b534c |
completed | March 11, 2026, 11:19 p.m. |
Created at: March 8, 2026, 3:02 p.m.