Triple
T37262246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Batavia shipwreck |
E924285
|
entity |
| Predicate | commanderOfShip |
P64599
|
FINISHED |
| Object |
Francisco Pelsaert
Francisco Pelsaert was a 17th-century Dutch East India Company merchant and ship’s commander best known for his role in the infamous Batavia shipwreck and the brutal mutiny and massacre that followed.
|
E2220450
|
NE FINISHED |
How this triple was built (3 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: Francisco Pelsaert | Statement: [Batavia shipwreck, commanderOfShip, Francisco Pelsaert]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Francisco Pelsaert Triple: [Batavia shipwreck, commanderOfShip, Francisco Pelsaert]
Generated description
Francisco Pelsaert was a 17th-century Dutch East India Company merchant and ship’s commander best known for his role in the infamous Batavia shipwreck and the brutal mutiny and massacre that followed.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commanderOfShip Context triple: [Batavia shipwreck, commanderOfShip, Francisco Pelsaert]
-
A.
captain
Indicates that one entity serves as the leader or person in command of another entity, typically a team, group, or vessel.
-
B.
commander
Indicates that one entity holds authoritative military or organizational control over another entity or group.
-
C.
commanderOfAttackedShip
Indicates that one entity is the commanding officer of a ship that is the target of an attack.
-
D.
commanderNationality
Indicates the national affiliation or citizenship of a given commander.
-
E.
commanderOnBoard
chosen
Indicates that a specific individual holds the role of commanding officer on a particular vehicle, vessel, or craft during its operation.
- F. None of above.
Provenance (6 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_69f76eabd6c481909d414a80a1345c98 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fdb45537288190b6791078d4a6899f |
completed | May 8, 2026, 10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40512ab58c8190b28643a685ab7c82 |
completed | June 27, 2026, 10:39 p.m. |
| NEDg | Description generation | batch_6a4051f3e8d08190b2e0db9d03b3a57e |
completed | June 27, 2026, 10:43 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a4052c19cdc8190afb2e5e3f9374eaa |
completed | June 27, 2026, 10:46 p.m. |
| PD | Predicate disambiguation | batch_69fdb39ad96481908376d7def9fafc13 |
completed | May 8, 2026, 9:57 a.m. |
Created at: May 3, 2026, 4:15 p.m.