Triple
T37661477
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | End Ship |
E937725
|
entity |
| Predicate | secondaryUniqueLoot |
P200733
|
FINISHED |
| Object | Dragon Head |
—
|
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: Dragon Head | Statement: [End Ship, secondaryUniqueLoot, Dragon Head]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryUniqueLoot Context triple: [End Ship, secondaryUniqueLoot, Dragon Head]
-
A.
secondaryProducts
Indicates that certain entities arise as secondary or byproduct outputs from a primary process, activity, or production.
-
B.
secondaryResource
Indicates that a resource serves as a secondary, supporting, or auxiliary resource in relation to a primary one.
-
C.
secondOnlyTo
Indicates that one entity ranks immediately below another in degree, importance, or quality, with only that other entity surpassing it.
-
D.
secondaryCargo
Indicates that an entity serves as an additional or auxiliary cargo associated with a primary shipment or load.
-
E.
secondarySingle
Indicates that an entity serves as a secondary, but singular, counterpart or role in relation to another primary entity.
- F. None of above. chosen
Provenance (4 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffa9677be08190852c8ef6c2545fed |
completed | May 9, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69ffa6570e2c8190a9d7b37f12b91d9a |
completed | May 9, 2026, 9:25 p.m. |
| PDg | Predicate description generation | batch_69ffa96638108190942dcfbe0516c37a |
completed | May 9, 2026, 9:38 p.m. |
Created at: May 3, 2026, 4:18 p.m.