Triple
T30971271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexander family, Earls of Caledon |
E789103
|
entity |
| Predicate | hasEarlierTitle |
P155834
|
FINISHED |
| Object |
Viscount Caledon
Viscount Caledon is a noble title in the Peerage of Ireland that historically served as a subsidiary or earlier rank associated with the Alexander family, later elevated to the Earls of Caledon.
|
E1956340
|
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: Viscount Caledon | Statement: [Alexander family, Earls of Caledon, hasEarlierTitle, Viscount Caledon]
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: Viscount Caledon Triple: [Alexander family, Earls of Caledon, hasEarlierTitle, Viscount Caledon]
Generated description
Viscount Caledon is a noble title in the Peerage of Ireland that historically served as a subsidiary or earlier rank associated with the Alexander family, later elevated to the Earls of Caledon.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEarlierTitle Context triple: [Alexander family, Earls of Caledon, hasEarlierTitle, Viscount Caledon]
-
A.
hasLaterTitle
Indicates that one title occurs chronologically after another title in a sequence or timeline.
-
B.
hasFormerTitle
chosen
Indicates that an entity previously held a specific title or position but no longer does.
-
C.
hasTitleSince
Indicates that an entity has held a particular title continuously starting from a specified point in time.
-
D.
replacedEarlierTitle
Indicates that one title or designation has been superseded by an earlier title that it replaced in a sequence of naming or labeling.
-
E.
hadTitle
Indicates that an entity held or was assigned a specific title or formal designation.
- 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_69f224c3a6b48190951add9b7b7f0271 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6953bafb88190a860e9c68a3dd4b2 |
completed | May 3, 2026, 12:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2a1e0d384481909680beb505ef2377 |
completed | June 11, 2026, 2:31 a.m. |
| NEDg | Description generation | batch_6a2a469f15ec81909b9e8071b4a72d88 |
completed | June 11, 2026, 5:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2a47dad0588190bf7905543950c601 |
completed | June 11, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_69f690ef92308190903a54fc74233269 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 29, 2026, 8:54 p.m.