Triple
T32050338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thos. Greene |
E818473
|
entity |
| Predicate | hasAbbreviationExpansionRule |
P127294
|
FINISHED |
| Object |
"Thos." expands to "Thomas"
Thos. Greene is an individual whose given name is the common English name Thomas, with "Thos." serving as its standard abbreviation.
|
E1988417
|
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: "Thos." expands to "Thomas" | Statement: [Thos. Greene, hasAbbreviationExpansionRule, "Thos." expands to "Thomas"]
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: "Thos." expands to "Thomas" Triple: [Thos. Greene, hasAbbreviationExpansionRule, "Thos." expands to "Thomas"]
Generated description
Thos. Greene is an individual whose given name is the common English name Thomas, with "Thos." serving as its standard abbreviation.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAbbreviationExpansionRule Context triple: [Thos. Greene, hasAbbreviationExpansionRule, "Thos." expands to "Thomas"]
-
A.
hasAbbreviationPattern
Indicates that there is a systematic abbreviation relationship between two strings, where one follows a recognizable pattern derived from the other.
-
B.
hasAbbreviationStatus
Indicates that an entity has a particular status or condition regarding its abbreviation (e.g., whether it is abbreviated, how, or to what extent).
-
C.
hasAbbreviationOrForm
chosen
Indicates that one entity serves as an abbreviation, shortened form, or alternative written form of another entity.
-
D.
isAbbreviation
Indicates that one term is a shortened or abbreviated form of another term.
-
E.
canBeUsedWithAbbreviation
Indicates that one entity (such as a term, phrase, or expression) is suitable to be used together with a particular abbreviation.
- 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_69f348fcfb648190859f6be5e04b7cfe |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b4c884148190be2cb7d9b354d17f |
completed | May 3, 2026, 2:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2ed5014dc48190a867e1417199d589 |
completed | June 14, 2026, 4:21 p.m. |
| NEDg | Description generation | batch_6a2ed5c14c4c8190965782d998ae7f2b |
completed | June 14, 2026, 4:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2ed747be30819082b3f0e05dc1f118 |
completed | June 14, 2026, 4:31 p.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:20 a.m.