Triple
T16378245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shardlake series |
E397731
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Tombland |
E397737
|
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: Tombland | Statement: [Shardlake series, hasPart, Tombland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tombland Context triple: [Shardlake series, hasPart, Tombland]
-
A.
Tombland
chosen
Tombland is a historical crime novel by C.J. Sansom featuring lawyer-detective Matthew Shardlake, set amid the political and social unrest of 16th-century England.
-
B.
Kingdom of Bone
The Kingdom of Bone was a historical Bugis state in South Sulawesi, Indonesia, known for its influential role in regional politics and trade before and during the early colonial period.
-
C.
Abarat
Abarat is a dark fantasy novel series by Clive Barker that follows a young girl’s adventures across a surreal archipelago of islands, each fixed at a different hour of the day.
-
D.
Lord of Tod
Lord of Tod is an epithet of the ancient Egyptian war god Montu, highlighting his role as a powerful local deity associated with the city of Tod in Upper Egypt.
-
E.
The Ruin
The Ruin is a melancholic Old English poem reflecting on the crumbling remains of a once-great stone city and the transience of human achievements.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e319d97e00819094aa094f52a5a93e |
completed | April 18, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00356658e881908131a3c60ed5499d |
completed | May 10, 2026, 7:36 a.m. |
Created at: April 10, 2026, 5:08 a.m.