Triple
T23017540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treasure Island (fictional island) |
E573071
|
entity |
| Predicate | treasureSoughtBy |
P97517
|
FINISHED |
| Object | Jim Hawkins and his allies |
—
|
LITERAL 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: Jim Hawkins and his allies | Statement: [Treasure Island (fictional island), treasureSoughtBy, Jim Hawkins and his allies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treasureSoughtBy Context triple: [Treasure Island (fictional island), treasureSoughtBy, Jim Hawkins and his allies]
-
A.
treasureInvolved
Indicates that a situation, event, or action involves or is related to treasure in some significant way.
-
B.
treasureMadeFor
Indicates that a treasure was specifically created, crafted, or designated for a particular recipient, purpose, or context.
-
C.
featuresTreasureHunt
chosen
Indicates that something includes or offers a treasure hunt activity or experience.
-
D.
plunderedItem
Indicates that an item has been taken or looted by force, typically during a raid, conflict, or act of theft.
-
E.
EnglishTreasureCaptured
Indicates that an English-controlled treasure or valuable asset has been seized or taken by another party.
- F. None of above.
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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e64a4c8190b8d29ed638c7fef8 |
completed | April 29, 2026, 4:07 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9cd5488190bcd23183179f48cd |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:52 p.m.